Borrowing it
Nothing to install: this file belongs to theshadow27/mcp-cli. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/theshadow27/mcp-cli/main/.claude/skills/rule-author/SKILL.mdgit clone --depth 1 https://github.com/theshadow27/mcp-cliWrote 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/theshadow27/mcp-cli/rule-author)<a href="https://agentmods.dev/skills/theshadow27/mcp-cli/rule-author"><img src="https://agentmods.dev/badge/skills/theshadow27/mcp-cli/rule-author/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/theshadow27/mcp-cli/rule-author"><img src="https://agentmods.dev/badge/skills/theshadow27/mcp-cli/rule-author.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 | $0.00160 | $0.01192 |
| Opus 5.5 | $0.00064 | $0.00477 |
| Sonnet 5.5 | $0.00032 | $0.00238 |
| Haiku 4.5 | $0.00016 | $0.00119 |
Grade A, and why
rule-author 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 2mo 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 — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Rule Author
The rule lifecycle is harvest → init → add. This skill routes on its argument:
/rule-author harvest— mine merged PRs for recurring author mistakes that could become rules. Seereferences/harvest.md./rule-author init— bootstrap the rule engine into a repo. Seereferences/rule-engine.md./rule-author add <rule>— author a new rule. Seereferences/new-rule.md.- no argument — this overview + the "is this a good rule?" triage below.
Why rules exist
A rule mechanizes a recurring mistake so review rounds and CI minutes are spent on judgment, not on catching the same avoidable bug again and again. Rules are part of the project's definition of done: the doing-it-wrong sweep runs inside am-i-done, which is the single gate executed identically at pre-commit and in CI. That's the whole value — it shifts failures left: a violation fails in seconds on the author's machine instead of surfacing minutes later in CI (or worse, never, if the gate is incomplete). And because mcp-cli is built by autonomous agents, rules are agentic guardrails: an implementer that doesn't know a convention gets caught mechanically instead of shipping the mistake into main. One rule is one scripts/rules/<id>.rule.ts file — not a new package.json script. New rules go behind the single doing-it-wrong / am-i-done entry points.
When to use this skill
- Writing a new rule from a known recurring mistake (e.g. a
/rule-author harvestfinding). - Refining a rule that's too broad (false positives) or too narrow (misses the shape).
- Judging whether a proposed invariant should be a rule at all.
- Migrating a legacy standalone
scripts/check-*.tsinto the engine. - Standing the engine up in a new repository.
References
references/harvest.md—/rule-author harvest: the survey → cluster → decide pipeline for mining merged-PR review comments. The per-agent classifier prompt lives inreferences/extract.mdand the extractor inscripts/extract-pr.ts.references/new-rule.md— how to author a.rule.ts: the API, regex-vs-AST decision, fixtures (minimal, not elaborate), writing guidance that names the cause, and the add-rule→show-red→remediate-in-the-same-PR discipline.references/rule-engine.md— a from-scratch description of the engine (every_engine/component, the entry scripts, and how the gate is wired). Use this when copying the engine to a new repo so you don't re-derive the layout each time.
What ships with it
5 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.
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.
- 2mo ago First seen · 43 lines · 160 tokens per session scan A 3e3bd81bcb36
rule-author is a skill published in the GitHub repository theshadow27/mcp-cli (2 stars, last pushed 3d ago), licensed MIT. It adds 160 tokens to every session and 1,192 once invoked, about $0.0006 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.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…
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…