Pick the dsh-aris corpus fixes back to main (#415)
Pick the dsh-aris corpus fixes back to main
This commit is contained in:
Yang Ruofeng
@@ -8,7 +8,9 @@
|
||||
|
||||
[](https://huggingface.co/papers/2605.03042) · [](https://wanshuiyin.github.io/Auto-claude-code-research-in-sleep/ARIS_INTRO.html) · [](docs/aris_intro_slides.pdf) · [](AGENT_GUIDE.md) · [](https://mp.weixin.qq.com/s/tDniVryVGjDkkkWl-5sTkQ) · [](https://github.com/VoltAgent/awesome-agent-skills) · [-orange?style=flat)](https://aidigitalcrew.com) · [](https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep/stargazers) · [💬 Join Community](#community) · [](#citation)
|
||||
|
||||
💡 *Use ARIS as a skill-based workflow in [Claude Code](https://docs.anthropic.com/en/docs/claude-code) / [Codex CLI](skills/skills-codex/) / [Cursor](docs/CURSOR_ADAPTATION.md) / [Trae](docs/TRAE_ARIS_RUNBOOK_EN.md) / [Antigravity](docs/ANTIGRAVITY_ADAPTATION.md) / [GitHub Copilot CLI](docs/COPILOT_CLI_ADAPTATION.md) / [OpenClaw](docs/OPENCLAW_ADAPTATION.md), or get the full experience with the standalone **[ARIS-Code](docs/ARIS-Code-README_EN.md)** CLI — enjoy any way you like!*
|
||||
💡 *Use ARIS as a skill-based workflow in [Claude Code](https://docs.anthropic.com/en/docs/claude-code) / [Codex CLI](skills/skills-codex/) / [Cursor](docs/CURSOR_ADAPTATION.md) / [Trae](docs/TRAE_ARIS_RUNBOOK_EN.md) / [Antigravity](docs/ANTIGRAVITY_ADAPTATION.md) / [GitHub Copilot CLI](docs/COPILOT_CLI_ADAPTATION.md) / [OpenClaw](docs/OPENCLAW_ADAPTATION.md) / [DeepSeek Harness](https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep/tree/dsh-aris#readme), or get the full experience with the standalone **[ARIS-Code](docs/ARIS-Code-README_EN.md)** CLI — enjoy any way you like!*
|
||||
|
||||
🐋 **On DeepSeek Harness it installs as one plugin:** `dsh plugin --profile web add dsh-aris` — all 82 skills unchanged, Codex still the independent reviewer. Setup and limits on the [`dsh-aris` branch](https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep/tree/dsh-aris#readme).
|
||||
|
||||
🌱 *ARIS is a methodology, not a platform. What matters is the research workflow — take it wherever you go.*
|
||||
|
||||
|
||||
+3
-1
@@ -8,7 +8,9 @@
|
||||
|
||||
[](https://huggingface.co/papers/2605.03042) · [](https://wanshuiyin.github.io/Auto-claude-code-research-in-sleep/ARIS_INTRO.html) · [](docs/aris_intro_slides.pdf) · [](AGENT_GUIDE.md) · [](https://mp.weixin.qq.com/s/tDniVryVGjDkkkWl-5sTkQ) · [](https://github.com/VoltAgent/awesome-agent-skills) · [-orange?style=flat)](https://aidigitalcrew.com) · [](https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep/stargazers) · [💬 加入交流群](#community) · [](#citation)
|
||||
|
||||
💡 *在 [Claude Code](https://docs.anthropic.com/en/docs/claude-code) / [Codex CLI](skills/skills-codex/) / [Cursor](docs/CURSOR_ADAPTATION.md) / [Trae](docs/TRAE_ARIS_RUNBOOK_CN.md) / [Antigravity](docs/ANTIGRAVITY_ADAPTATION_CN.md) / [GitHub Copilot CLI](docs/COPILOT_CLI_ADAPTATION.md) / [OpenClaw](docs/OPENCLAW_ADAPTATION.md) 里以 skill-based workflow 用 ARIS，或用独立的 **[ARIS-Code](docs/ARIS-Code-README_CN.md)** CLI 完整版体验——任你选！*
|
||||
💡 *在 [Claude Code](https://docs.anthropic.com/en/docs/claude-code) / [Codex CLI](skills/skills-codex/) / [Cursor](docs/CURSOR_ADAPTATION.md) / [Trae](docs/TRAE_ARIS_RUNBOOK_CN.md) / [Antigravity](docs/ANTIGRAVITY_ADAPTATION_CN.md) / [GitHub Copilot CLI](docs/COPILOT_CLI_ADAPTATION.md) / [OpenClaw](docs/OPENCLAW_ADAPTATION.md) / [DeepSeek Harness](https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep/blob/dsh-aris/README_CN.md) 里以 skill-based workflow 用 ARIS，或用独立的 **[ARIS-Code](docs/ARIS-Code-README_CN.md)** CLI 完整版体验——任你选！*
|
||||
|
||||
🐋 **在 DeepSeek Harness 上，ARIS 是一个插件：** `dsh plugin --profile web add dsh-aris` —— 82 个技能零改动，审稿人仍是 Codex。安装与限制见 [`dsh-aris` 分支](https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep/blob/dsh-aris/README_CN.md)。
|
||||
|
||||
🌱 *ARIS 是方法论，不是平台。重要的是科研工作流——带着它去任何地方。*
|
||||
|
||||
|
||||
@@ -396,8 +396,12 @@ mcp__codex__codex:
|
||||
machine — a malicious local user is NOT in the threat model.
|
||||
2. Do NOT propose SHA / hash / content-fingerprint / digest-binding schemes.
|
||||
Reporting a real defect in hashing code that already exists is fine.
|
||||
3. NO defensive scaffolding: no feature flags, migration frameworks, compat
|
||||
layers, or wrappers added for cases that do not occur in practice.
|
||||
3. NO speculative machinery: do not add feature flags, migration frameworks,
|
||||
compat layers, wrappers, pins, or similar mechanisms unless evidence shows
|
||||
a current repo defect they fix or an explicit existing invariant they must
|
||||
preserve. "Load-bearing", "compatibility", and "not scaffolding" are labels,
|
||||
not evidence. Point to the failing path/artifact or invariant, and check the
|
||||
proposal's factual premises, such as whether a named package version exists.
|
||||
4. NO corner-case obsession: exotic encodings, symlink races, RTL text and
|
||||
millisecond races are out of scope unless you can show the case arises here.
|
||||
5. Where a rubric or checklist is genuinely needed, do not over-mechanize
|
||||
@@ -457,8 +461,12 @@ mcp__codex__codex:
|
||||
machine — a malicious local user is NOT in the threat model.
|
||||
2. Do NOT propose SHA / hash / content-fingerprint / digest-binding schemes.
|
||||
Reporting a real defect in hashing code that already exists is fine.
|
||||
3. NO defensive scaffolding: no feature flags, migration frameworks, compat
|
||||
layers, or wrappers added for cases that do not occur in practice.
|
||||
3. NO speculative machinery: do not add feature flags, migration frameworks,
|
||||
compat layers, wrappers, pins, or similar mechanisms unless evidence shows
|
||||
a current repo defect they fix or an explicit existing invariant they must
|
||||
preserve. "Load-bearing", "compatibility", and "not scaffolding" are labels,
|
||||
not evidence. Point to the failing path/artifact or invariant, and check the
|
||||
proposal's factual premises, such as whether a named package version exists.
|
||||
4. NO corner-case obsession: exotic encodings, symlink races, RTL text and
|
||||
millisecond races are out of scope unless you can show the case arises here.
|
||||
5. Where a rubric or checklist is genuinely needed, do not over-mechanize
|
||||
@@ -512,8 +520,12 @@ this repo actually produces it. Then keep the fix in scope:
|
||||
machine — a malicious local user is NOT in the threat model.
|
||||
2. Do NOT propose SHA / hash / content-fingerprint / digest-binding schemes.
|
||||
Reporting a real defect in hashing code that already exists is fine.
|
||||
3. NO defensive scaffolding: no feature flags, migration frameworks, compat
|
||||
layers, or wrappers added for cases that do not occur in practice.
|
||||
3. NO speculative machinery: do not add feature flags, migration frameworks,
|
||||
compat layers, wrappers, pins, or similar mechanisms unless evidence shows
|
||||
a current repo defect they fix or an explicit existing invariant they must
|
||||
preserve. "Load-bearing", "compatibility", and "not scaffolding" are labels,
|
||||
not evidence. Point to the failing path/artifact or invariant, and check the
|
||||
proposal's factual premises, such as whether a named package version exists.
|
||||
4. NO corner-case obsession: exotic encodings, symlink races, RTL text and
|
||||
millisecond races are out of scope unless you can show the case arises here.
|
||||
5. Where a rubric or checklist is genuinely needed, do not over-mechanize
|
||||
@@ -1023,8 +1035,12 @@ this repo actually produces it. Then keep the fix in scope:
|
||||
machine — a malicious local user is NOT in the threat model.
|
||||
2. Do NOT propose SHA / hash / content-fingerprint / digest-binding schemes.
|
||||
Reporting a real defect in hashing code that already exists is fine.
|
||||
3. NO defensive scaffolding: no feature flags, migration frameworks, compat
|
||||
layers, or wrappers added for cases that do not occur in practice.
|
||||
3. NO speculative machinery: do not add feature flags, migration frameworks,
|
||||
compat layers, wrappers, pins, or similar mechanisms unless evidence shows
|
||||
a current repo defect they fix or an explicit existing invariant they must
|
||||
preserve. "Load-bearing", "compatibility", and "not scaffolding" are labels,
|
||||
not evidence. Point to the failing path/artifact or invariant, and check the
|
||||
proposal's factual premises, such as whether a named package version exists.
|
||||
4. NO corner-case obsession: exotic encodings, symlink races, RTL text and
|
||||
millisecond races are out of scope unless you can show the case arises here.
|
||||
5. Where a rubric or checklist is genuinely needed, do not over-mechanize
|
||||
@@ -1066,8 +1082,12 @@ copilot --agent "$REVIEWER_PROFILE" --model "$REVIEWER_MODEL" \
|
||||
machine — a malicious local user is NOT in the threat model.
|
||||
2. Do NOT propose SHA / hash / content-fingerprint / digest-binding schemes.
|
||||
Reporting a real defect in hashing code that already exists is fine.
|
||||
3. NO defensive scaffolding: no feature flags, migration frameworks, compat
|
||||
layers, or wrappers added for cases that do not occur in practice.
|
||||
3. NO speculative machinery: do not add feature flags, migration frameworks,
|
||||
compat layers, wrappers, pins, or similar mechanisms unless evidence shows
|
||||
a current repo defect they fix or an explicit existing invariant they must
|
||||
preserve. "Load-bearing", "compatibility", and "not scaffolding" are labels,
|
||||
not evidence. Point to the failing path/artifact or invariant, and check the
|
||||
proposal's factual premises, such as whether a named package version exists.
|
||||
4. NO corner-case obsession: exotic encodings, symlink races, RTL text and
|
||||
millisecond races are out of scope unless you can show the case arises here.
|
||||
5. Where a rubric or checklist is genuinely needed, do not over-mechanize
|
||||
|
||||
@@ -149,8 +149,12 @@ mcp__codex__codex:
|
||||
machine — a malicious local user is NOT in the threat model.
|
||||
2. Do NOT propose SHA / hash / content-fingerprint / digest-binding schemes.
|
||||
Reporting a real defect in hashing code that already exists is fine.
|
||||
3. NO defensive scaffolding: no feature flags, migration frameworks, compat
|
||||
layers, or wrappers added for cases that do not occur in practice.
|
||||
3. NO speculative machinery: do not add feature flags, migration frameworks,
|
||||
compat layers, wrappers, pins, or similar mechanisms unless evidence shows
|
||||
a current repo defect they fix or an explicit existing invariant they must
|
||||
preserve. "Load-bearing", "compatibility", and "not scaffolding" are labels,
|
||||
not evidence. Point to the failing path/artifact or invariant, and check the
|
||||
proposal's factual premises, such as whether a named package version exists.
|
||||
4. NO corner-case obsession: exotic encodings, symlink races, RTL text and
|
||||
millisecond races are out of scope unless you can show the case arises here.
|
||||
5. Where a rubric or checklist is genuinely needed, do not over-mechanize
|
||||
|
||||
@@ -28,7 +28,12 @@ Audit target: **$ARGUMENTS**
|
||||
- **ANTI_AR_COMMIT = `b47af6f983b38347b6d2110379e266400597cf66`** — the SHA-pin.
|
||||
The launcher NEVER tracks upstream HEAD; bumping this constant is a reviewed
|
||||
change (see Pin-bump checklist).
|
||||
- **CLONE_DIR = `~/.claude/anti-autoresearch`** — the pinned working copy.
|
||||
- **CLONE_DIR = `~/.aris/anti-autoresearch`** — the pinned working copy. Host-neutral
|
||||
on purpose: ARIS also runs on DeepSeek Harness, Codex CLI, Cursor, Trae,
|
||||
Antigravity and Copilot CLI, where `~/.claude/` would name an installation the
|
||||
user does not have. An older clone at `~/.claude/anti-autoresearch` is unused;
|
||||
move it and its `.aris_eval_ok_*` receipt only to keep an offline
|
||||
deterministic-only run working, otherwise delete it whenever convenient.
|
||||
- **NO REVIEWER KNOBS.** This launcher exposes no reviewer model/effort
|
||||
parameters and never maps ARIS `— effort:` onto upstream settings. The
|
||||
pinned upstream runs exactly what it pins (`gpt-5.6-sol` + `xhigh`, its own
|
||||
@@ -43,9 +48,10 @@ Audit target: **$ARGUMENTS**
|
||||
## Step 0 — Bootstrap the pin (idempotent)
|
||||
|
||||
```bash
|
||||
CLONE_DIR="$HOME/.claude/anti-autoresearch"
|
||||
CLONE_DIR="$HOME/.aris/anti-autoresearch"
|
||||
ANTI_AR_COMMIT="b47af6f983b38347b6d2110379e266400597cf66"
|
||||
|
||||
mkdir -p "$HOME/.aris"
|
||||
if [ ! -d "$CLONE_DIR/.git" ]; then
|
||||
git clone --no-checkout https://github.com/wanshuiyin/Anti-Autoresearch.git "$CLONE_DIR"
|
||||
fi
|
||||
@@ -262,7 +268,9 @@ Upstream ships no Codex-native pack; its auditor skills are Claude-Code
|
||||
contracts. A Codex-native session may run upstream's **deterministic-only
|
||||
mode** (numeric core + adjudicator with an all-`review_unavailable` coverage
|
||||
map — honestly scoped: it can flag, it can never say CLEAN). The full
|
||||
nine-dimension sweep requires a Claude Code session. Translating upstream's
|
||||
nine-dimension sweep requires a host that can execute upstream's Claude-Code
|
||||
contracts unchanged — Claude Code and the `dsh-aris` bundle on DeepSeek Harness
|
||||
are the known ones. Translating upstream's
|
||||
reviewer calls into `spawn_agent` on the fly is REWRITING an upstream
|
||||
contract — forbidden.
|
||||
|
||||
|
||||
@@ -293,8 +293,12 @@ mcp__codex__codex:
|
||||
machine — a malicious local user is NOT in the threat model.
|
||||
2. Do NOT propose SHA / hash / content-fingerprint / digest-binding schemes.
|
||||
Reporting a real defect in hashing code that already exists is fine.
|
||||
3. NO defensive scaffolding: no feature flags, migration frameworks, compat
|
||||
layers, or wrappers added for cases that do not occur in practice.
|
||||
3. NO speculative machinery: do not add feature flags, migration frameworks,
|
||||
compat layers, wrappers, pins, or similar mechanisms unless evidence shows
|
||||
a current repo defect they fix or an explicit existing invariant they must
|
||||
preserve. "Load-bearing", "compatibility", and "not scaffolding" are labels,
|
||||
not evidence. Point to the failing path/artifact or invariant, and check the
|
||||
proposal's factual premises, such as whether a named package version exists.
|
||||
4. NO corner-case obsession: exotic encodings, symlink races, RTL text and
|
||||
millisecond races are out of scope unless you can show the case arises here.
|
||||
5. Where a rubric or checklist is genuinely needed, do not over-mechanize
|
||||
|
||||
@@ -224,8 +224,12 @@ contract is what gets graded.)
|
||||
machine — a malicious local user is NOT in the threat model.
|
||||
2. Do NOT propose SHA / hash / content-fingerprint / digest-binding schemes.
|
||||
Reporting a real defect in hashing code that already exists is fine.
|
||||
3. NO defensive scaffolding: no feature flags, migration frameworks, compat
|
||||
layers, or wrappers added for cases that do not occur in practice.
|
||||
3. NO speculative machinery: do not add feature flags, migration frameworks,
|
||||
compat layers, wrappers, pins, or similar mechanisms unless evidence shows
|
||||
a current repo defect they fix or an explicit existing invariant they must
|
||||
preserve. "Load-bearing", "compatibility", and "not scaffolding" are labels,
|
||||
not evidence. Point to the failing path/artifact or invariant, and check the
|
||||
proposal's factual premises, such as whether a named package version exists.
|
||||
4. NO corner-case obsession: exotic encodings, symlink races, RTL text and
|
||||
millisecond races are out of scope unless you can show the case arises here.
|
||||
5. Where a rubric or checklist is genuinely needed, do not over-mechanize
|
||||
|
||||
@@ -20,8 +20,12 @@ this repo actually produces it. Then keep the fix in scope:
|
||||
machine — a malicious local user is NOT in the threat model.
|
||||
2. Do NOT propose SHA / hash / content-fingerprint / digest-binding schemes.
|
||||
Reporting a real defect in hashing code that already exists is fine.
|
||||
3. NO defensive scaffolding: no feature flags, migration frameworks, compat
|
||||
layers, or wrappers added for cases that do not occur in practice.
|
||||
3. NO speculative machinery: do not add feature flags, migration frameworks,
|
||||
compat layers, wrappers, pins, or similar mechanisms unless evidence shows
|
||||
a current repo defect they fix or an explicit existing invariant they must
|
||||
preserve. "Load-bearing", "compatibility", and "not scaffolding" are labels,
|
||||
not evidence. Point to the failing path/artifact or invariant, and check the
|
||||
proposal's factual premises, such as whether a named package version exists.
|
||||
4. NO corner-case obsession: exotic encodings, symlink races, RTL text and
|
||||
millisecond races are out of scope unless you can show the case arises here.
|
||||
5. Where a rubric or checklist is genuinely needed, do not over-mechanize
|
||||
|
||||
@@ -165,8 +165,12 @@ mcp__claude-review__review_start:
|
||||
machine — a malicious local user is NOT in the threat model.
|
||||
2. Do NOT propose SHA / hash / content-fingerprint / digest-binding schemes.
|
||||
Reporting a real defect in hashing code that already exists is fine.
|
||||
3. NO defensive scaffolding: no feature flags, migration frameworks, compat
|
||||
layers, or wrappers added for cases that do not occur in practice.
|
||||
3. NO speculative machinery: do not add feature flags, migration frameworks,
|
||||
compat layers, wrappers, pins, or similar mechanisms unless evidence shows
|
||||
a current repo defect they fix or an explicit existing invariant they must
|
||||
preserve. "Load-bearing", "compatibility", and "not scaffolding" are labels,
|
||||
not evidence. Point to the failing path/artifact or invariant, and check the
|
||||
proposal's factual premises, such as whether a named package version exists.
|
||||
4. NO corner-case obsession: exotic encodings, symlink races, RTL text and
|
||||
millisecond races are out of scope unless you can show the case arises here.
|
||||
5. Where a rubric or checklist is genuinely needed, do not over-mechanize
|
||||
@@ -452,8 +456,12 @@ mcp__claude-review__review_reply_start:
|
||||
machine — a malicious local user is NOT in the threat model.
|
||||
2. Do NOT propose SHA / hash / content-fingerprint / digest-binding schemes.
|
||||
Reporting a real defect in hashing code that already exists is fine.
|
||||
3. NO defensive scaffolding: no feature flags, migration frameworks, compat
|
||||
layers, or wrappers added for cases that do not occur in practice.
|
||||
3. NO speculative machinery: do not add feature flags, migration frameworks,
|
||||
compat layers, wrappers, pins, or similar mechanisms unless evidence shows
|
||||
a current repo defect they fix or an explicit existing invariant they must
|
||||
preserve. "Load-bearing", "compatibility", and "not scaffolding" are labels,
|
||||
not evidence. Point to the failing path/artifact or invariant, and check the
|
||||
proposal's factual premises, such as whether a named package version exists.
|
||||
4. NO corner-case obsession: exotic encodings, symlink races, RTL text and
|
||||
millisecond races are out of scope unless you can show the case arises here.
|
||||
5. Where a rubric or checklist is genuinely needed, do not over-mechanize
|
||||
|
||||
@@ -95,8 +95,12 @@ mcp__gemini-review__review_start:
|
||||
machine — a malicious local user is NOT in the threat model.
|
||||
2. Do NOT propose SHA / hash / content-fingerprint / digest-binding schemes.
|
||||
Reporting a real defect in hashing code that already exists is fine.
|
||||
3. NO defensive scaffolding: no feature flags, migration frameworks, compat
|
||||
layers, or wrappers added for cases that do not occur in practice.
|
||||
3. NO speculative machinery: do not add feature flags, migration frameworks,
|
||||
compat layers, wrappers, pins, or similar mechanisms unless evidence shows
|
||||
a current repo defect they fix or an explicit existing invariant they must
|
||||
preserve. "Load-bearing", "compatibility", and "not scaffolding" are labels,
|
||||
not evidence. Point to the failing path/artifact or invariant, and check the
|
||||
proposal's factual premises, such as whether a named package version exists.
|
||||
4. NO corner-case obsession: exotic encodings, symlink races, RTL text and
|
||||
millisecond races are out of scope unless you can show the case arises here.
|
||||
5. Where a rubric or checklist is genuinely needed, do not over-mechanize
|
||||
@@ -280,8 +284,12 @@ mcp__gemini-review__review_reply_start:
|
||||
machine — a malicious local user is NOT in the threat model.
|
||||
2. Do NOT propose SHA / hash / content-fingerprint / digest-binding schemes.
|
||||
Reporting a real defect in hashing code that already exists is fine.
|
||||
3. NO defensive scaffolding: no feature flags, migration frameworks, compat
|
||||
layers, or wrappers added for cases that do not occur in practice.
|
||||
3. NO speculative machinery: do not add feature flags, migration frameworks,
|
||||
compat layers, wrappers, pins, or similar mechanisms unless evidence shows
|
||||
a current repo defect they fix or an explicit existing invariant they must
|
||||
preserve. "Load-bearing", "compatibility", and "not scaffolding" are labels,
|
||||
not evidence. Point to the failing path/artifact or invariant, and check the
|
||||
proposal's factual premises, such as whether a named package version exists.
|
||||
4. NO corner-case obsession: exotic encodings, symlink races, RTL text and
|
||||
millisecond races are out of scope unless you can show the case arises here.
|
||||
5. Where a rubric or checklist is genuinely needed, do not over-mechanize
|
||||
|
||||
@@ -161,8 +161,12 @@ spawn_agent:
|
||||
machine — a malicious local user is NOT in the threat model.
|
||||
2. Do NOT propose SHA / hash / content-fingerprint / digest-binding schemes.
|
||||
Reporting a real defect in hashing code that already exists is fine.
|
||||
3. NO defensive scaffolding: no feature flags, migration frameworks, compat
|
||||
layers, or wrappers added for cases that do not occur in practice.
|
||||
3. NO speculative machinery: do not add feature flags, migration frameworks,
|
||||
compat layers, wrappers, pins, or similar mechanisms unless evidence shows
|
||||
a current repo defect they fix or an explicit existing invariant they must
|
||||
preserve. "Load-bearing", "compatibility", and "not scaffolding" are labels,
|
||||
not evidence. Point to the failing path/artifact or invariant, and check the
|
||||
proposal's factual premises, such as whether a named package version exists.
|
||||
4. NO corner-case obsession: exotic encodings, symlink races, RTL text and
|
||||
millisecond races are out of scope unless you can show the case arises here.
|
||||
5. Where a rubric or checklist is genuinely needed, do not over-mechanize
|
||||
@@ -444,8 +448,12 @@ send_input:
|
||||
machine — a malicious local user is NOT in the threat model.
|
||||
2. Do NOT propose SHA / hash / content-fingerprint / digest-binding schemes.
|
||||
Reporting a real defect in hashing code that already exists is fine.
|
||||
3. NO defensive scaffolding: no feature flags, migration frameworks, compat
|
||||
layers, or wrappers added for cases that do not occur in practice.
|
||||
3. NO speculative machinery: do not add feature flags, migration frameworks,
|
||||
compat layers, wrappers, pins, or similar mechanisms unless evidence shows
|
||||
a current repo defect they fix or an explicit existing invariant they must
|
||||
preserve. "Load-bearing", "compatibility", and "not scaffolding" are labels,
|
||||
not evidence. Point to the failing path/artifact or invariant, and check the
|
||||
proposal's factual premises, such as whether a named package version exists.
|
||||
4. NO corner-case obsession: exotic encodings, symlink races, RTL text and
|
||||
millisecond races are out of scope unless you can show the case arises here.
|
||||
5. Where a rubric or checklist is genuinely needed, do not over-mechanize
|
||||
|
||||
@@ -149,8 +149,12 @@ spawn_agent:
|
||||
machine — a malicious local user is NOT in the threat model.
|
||||
2. Do NOT propose SHA / hash / content-fingerprint / digest-binding schemes.
|
||||
Reporting a real defect in hashing code that already exists is fine.
|
||||
3. NO defensive scaffolding: no feature flags, migration frameworks, compat
|
||||
layers, or wrappers added for cases that do not occur in practice.
|
||||
3. NO speculative machinery: do not add feature flags, migration frameworks,
|
||||
compat layers, wrappers, pins, or similar mechanisms unless evidence shows
|
||||
a current repo defect they fix or an explicit existing invariant they must
|
||||
preserve. "Load-bearing", "compatibility", and "not scaffolding" are labels,
|
||||
not evidence. Point to the failing path/artifact or invariant, and check the
|
||||
proposal's factual premises, such as whether a named package version exists.
|
||||
4. NO corner-case obsession: exotic encodings, symlink races, RTL text and
|
||||
millisecond races are out of scope unless you can show the case arises here.
|
||||
5. Where a rubric or checklist is genuinely needed, do not over-mechanize
|
||||
|
||||
@@ -24,14 +24,18 @@ Audit target: **$ARGUMENTS**
|
||||
- **ANTI_AR_REPO = `https://github.com/wanshuiyin/Anti-Autoresearch.git`**
|
||||
- **ANTI_AR_COMMIT = `b47af6f983b38347b6d2110379e266400597cf66`** — never
|
||||
tracks HEAD; bumping is a reviewed change (mainline Pin-bump checklist).
|
||||
- **CLONE_DIR = `~/.claude/anti-autoresearch`**
|
||||
- **CLONE_DIR = `~/.aris/anti-autoresearch`** — host-neutral. An older clone at
|
||||
`~/.claude/anti-autoresearch` is unused; move it and its `.aris_eval_ok_*`
|
||||
receipt to keep an offline deterministic-only run working — this pack's own
|
||||
mode — otherwise delete it whenever convenient.
|
||||
- **NO REVIEWER KNOBS** — and no `— effort:` mapping onto upstream settings.
|
||||
|
||||
## Step 0 — Bootstrap the pin (identical to mainline)
|
||||
|
||||
```bash
|
||||
CLONE_DIR="$HOME/.claude/anti-autoresearch"
|
||||
CLONE_DIR="$HOME/.aris/anti-autoresearch"
|
||||
ANTI_AR_COMMIT="b47af6f983b38347b6d2110379e266400597cf66"
|
||||
mkdir -p "$HOME/.aris"
|
||||
if [ ! -d "$CLONE_DIR/.git" ]; then
|
||||
git clone --no-checkout https://github.com/wanshuiyin/Anti-Autoresearch.git "$CLONE_DIR"
|
||||
fi
|
||||
|
||||
@@ -222,8 +222,12 @@ spawn_agent:
|
||||
machine — a malicious local user is NOT in the threat model.
|
||||
2. Do NOT propose SHA / hash / content-fingerprint / digest-binding schemes.
|
||||
Reporting a real defect in hashing code that already exists is fine.
|
||||
3. NO defensive scaffolding: no feature flags, migration frameworks, compat
|
||||
layers, or wrappers added for cases that do not occur in practice.
|
||||
3. NO speculative machinery: do not add feature flags, migration frameworks,
|
||||
compat layers, wrappers, pins, or similar mechanisms unless evidence shows
|
||||
a current repo defect they fix or an explicit existing invariant they must
|
||||
preserve. "Load-bearing", "compatibility", and "not scaffolding" are labels,
|
||||
not evidence. Point to the failing path/artifact or invariant, and check the
|
||||
proposal's factual premises, such as whether a named package version exists.
|
||||
4. NO corner-case obsession: exotic encodings, symlink races, RTL text and
|
||||
millisecond races are out of scope unless you can show the case arises here.
|
||||
5. Where a rubric or checklist is genuinely needed, do not over-mechanize
|
||||
|
||||
@@ -20,8 +20,12 @@ this repo actually produces it. Then keep the fix in scope:
|
||||
machine — a malicious local user is NOT in the threat model.
|
||||
2. Do NOT propose SHA / hash / content-fingerprint / digest-binding schemes.
|
||||
Reporting a real defect in hashing code that already exists is fine.
|
||||
3. NO defensive scaffolding: no feature flags, migration frameworks, compat
|
||||
layers, or wrappers added for cases that do not occur in practice.
|
||||
3. NO speculative machinery: do not add feature flags, migration frameworks,
|
||||
compat layers, wrappers, pins, or similar mechanisms unless evidence shows
|
||||
a current repo defect they fix or an explicit existing invariant they must
|
||||
preserve. "Load-bearing", "compatibility", and "not scaffolding" are labels,
|
||||
not evidence. Point to the failing path/artifact or invariant, and check the
|
||||
proposal's factual premises, such as whether a named package version exists.
|
||||
4. NO corner-case obsession: exotic encodings, symlink races, RTL text and
|
||||
millisecond races are out of scope unless you can show the case arises here.
|
||||
5. Where a rubric or checklist is genuinely needed, do not over-mechanize
|
||||
|
||||
Reference in New Issue
Block a user