Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add sfc-gh-myoung/ai_coding_rules --skill rule-reviewergit clone --depth 1 https://github.com/sfc-gh-myoung/ai_coding_rulesWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/sfc-gh-myoung/ai_coding_rules/rule-reviewer)<a href="https://agentmods.dev/skills/sfc-gh-myoung/ai_coding_rules/rule-reviewer"><img src="https://agentmods.dev/badge/skills/sfc-gh-myoung/ai_coding_rules/rule-reviewer/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/sfc-gh-myoung/ai_coding_rules/rule-reviewer"><img src="https://agentmods.dev/badge/skills/sfc-gh-myoung/ai_coding_rules/rule-reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00069 | $0.03628 |
| Opus 5.5 | $0.00028 | $0.01451 |
| Sonnet 5.5 | $0.00014 | $0.00726 |
| Haiku 4.5 | $0.00007 | $0.00363 |
Grade A, and why
rule-reviewer scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 20d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 233 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Rule Reviewer
Purpose
Execute comprehensive agent-centric reviews evaluating whether autonomous agents can execute rules without judgment calls.
For v4 rules, read the active schema and governance contract before applying the rubrics. Required H2 order is Scope, Contract, References, with four non-empty Contract subsections. Do not penalize omitted optional sections, fixed step/example counts, or a missing duplicate checklist. Structural checks and semantic review remain separate.
Use this skill when
- Reviewing rule files for agent executability (FULL mode)
- Auditing a specific dimension of a rule (FOCUSED mode)
- Checking rule staleness against the current codebase (STALENESS mode)
- Validating rule compliance with schema and conventions
- Scoring rule quality against the 6-dimension rubric
Quick Start
Use the rule-reviewer skill.
target_file: rules/200-python-core.md
review_date: 2026-01-06
review_mode: FULL
model: claude-sonnet-4-6
Output: reviews/rule-reviews/200-python-core-claude-sonnet-4-6-2026-01-06.json (canonical)
reviews/rule-reviews/200-python-core-claude-sonnet-4-6-2026-01-06.md (derived)
(With output_root: mytest/ → mytest/rule-reviews/200-python-core-claude-sonnet-4-6-2026-01-06.{json,md})
Scoring System (100 points)
6 scored dimensions, 100 points total. Hard caps apply for size (> 300 lines / > 350 lines) and blocking issues (≥ 6 / ≥ 10).
Quick reference:
| Dimension | Weight | Max |
|---|---|---|
| Actionability | 3.0 | 30 |
| Rule Size | 2.5 | 25 |
| Parsability | 1.5 | 15 |
| Completeness | 1.5 | 15 |
| Consistency | 1.0 | 10 |
| Cross-Agent Consistency | 0.5 | 5 |
Full scoring formula, hard-cap thresholds, per-dimension rubric file references, and example calculations: rubrics/scoring.md.
Review Modes
- FULL: All 6 scored dimensions (100 points max)
- FOCUSED: Actionability + Completeness only (45 points max)
- STALENESS: Informational staleness check (not scored)
What ships with it
44 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- CHANGELOG.md 11 KB
- examples/edge-cases.md 10 KB
- examples/focused-review.md 800 B
- examples/full-review.md 2.3 KB
- examples/project-file-review.md 6.5 KB
- examples/staleness-review.md 766 B
- references/gate-8.md 816 B
- references/rendered-review-format.md 3.1 KB
- references/retry-contract.md 3.3 KB
- references/REVIEW-OUTPUT-TEMPLATE.md 8.0 KB
- references/reviewer-defaults.yml 5.1 KB
- rubrics/_calibration-examples.md 3.0 KB
- rubrics/_overlap-resolution.md 5.7 KB
- rubrics/actionability.md 11 KB
- rubrics/completeness.md 14 KB
- rubrics/consistency.md 11 KB
- rubrics/cross-agent-consistency.md 8.0 KB
- rubrics/parsability.md 16 KB
- rubrics/rule-size.md 9.5 KB
- rubrics/scoring.md 1.5 KB
- rubrics/staleness.md 2.4 KB
- rubrics/token-efficiency.md 1.8 KB
- tests/test_gate7_integration.py 4.3 KB runs code
- tests/test-inputs.md 4.8 KB
- tests/test-modes.md 6.3 KB
- tests/test-outputs.md 5.8 KB
- tests/TESTING.md 8.4 KB
- workflows/bulk-coordination.md 1.1 KB
- workflows/determinism.md 2.5 KB
- workflows/dimension-subagent-template.md 8.2 KB
- workflows/doc-currency-check.md 3.5 KB
- workflows/error-handling.md 10 KB
- workflows/execution-discipline.md 1.7 KB
- workflows/file-write.md 3.8 KB
- workflows/input-validation.md 3.1 KB
- workflows/model-slugging.md 414 B
- workflows/parallel-execution.md 13 KB
- workflows/parameter-collection.md 5.5 KB
- workflows/review-execution.md 9.1 KB
- workflows/review-verification.md 5.6 KB
- workflows/schema-validation.md 3.5 KB
- workflows/score-aggregation.md 18 KB
- workflows/timing-integration.md 4.2 KB
- workflows/validation-checklists.md 1.1 KB
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 20d ago Changed · -155 lines 854e4a458c52
- 2mo ago First seen · 388 lines · 69 tokens per session scan A ba4906d0a5d2
rule-reviewer is a skill published in the GitHub repository sfc-gh-myoung/ai_coding_rules (8 stars, last pushed 2d ago), licensed Apache-2.0. It adds 69 tokens to every session and 3,628 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
autoreview
Structured code review through the shared OpenClaw agent-skills installation.
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
explore-unknowns
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…
asplos-writing-style
Use when drafting or revising ASPLOS prose — engineering the first two pages that rapid review actually reads, stating the cross-layer insight as one quotable sentence, structuring per-layer mechanism sections, writing bounded claims, and fitting everything into 11 self-contained pages that include figures and…