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 shimo4228/claude-harness --skill rfc-writergit clone --depth 1 https://github.com/shimo4228/claude-harnessWrote 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/shimo4228/claude-harness/rfc-writer)<a href="https://agentmods.dev/skills/shimo4228/claude-harness/rfc-writer"><img src="https://agentmods.dev/badge/skills/shimo4228/claude-harness/rfc-writer/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/shimo4228/claude-harness/rfc-writer"><img src="https://agentmods.dev/badge/skills/shimo4228/claude-harness/rfc-writer.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 | $0.00288 | $0.02049 |
| Opus 5 | $0.00144 | $0.01025 |
| Sonnet 5 | $0.00058 | $0.00410 |
| Haiku 4.5 | $0.00029 | $0.00205 |
Grade A, and why
rfc-writer 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 4d 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 — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.
RFC Writer — 公開台帳への起票
rfcs/ は提案と作業項目の公開台帳(判断は ADR-0049/0050)。この skill が規約の
唯一の正本で、各 repo の rfcs/README.md には規約を書かない — 複製した版は誰も
刈らず drift する。
0. 足切り — 起票しないことを先に判定する
Do not create an RFC for work that can be safely completed in the current session without preserving intent or state.
台帳は seam(セッション境界・判断待ち・条件待ち)へ intent と state を運ぶ器。 運ぶものが無い起票は純コスト(GTD の 2 分ルールの台帳版、2026-08-25 著者規約)。
- 逆は成り立つ: 今すぐ却下できる提案でも却下理由を残す価値があるなら起票してよい — それは intent の保存(公開判断記録が rfcs/ の存在理由)
- 起票のタイミングは seam が生まれた瞬間、入口の儀式ではない: plan → 実装で完結する 直実装は RFC 無しが既定 — 記録は commit(何を)と ADR(なぜ、判断が要るときだけ)が 担う。後追いで起票するのは足切りの前提が破れた瞬間: ① 実装がセッションを跨ぐ ことになった(in_progress + Status に経緯)② 人間の判断待ちで止まった(blocked + 3 行)③ 実装中に「やらない」と決めた(rejected / withdrawn、却下理由ごと terminal で 置く)。完了後の後追い起票はしない — それは ADR か commit log の領分
- 別軸の既存足切りはそのまま: review 指摘は「loop 自身を壊す欠陥」+ producer 引用のみ 即時起票(task-stocktake「レビュー指摘の起票規律」、ADR-0055 で再絞り込み)、 便乗型(「次に X を触る時に」)は台帳でなくコード側の注記
1. 起票手順
-
state: 提案は
draft、採用済みの作業項目はaccepted。語彙 9 語の定義・ 使い分け・blockedの 3 行は skill:task-stocktakeが正本(ここに複製しない) -
採番:
rfcs/の[0-9][0-9][0-9][0-9]-*.mdの最大番号 +1 を 4 桁 zero-pad。 欠番は再利用しない(docs/adr と同じ)。ファイル名NNNN-<kebab-slug>.md、 ID はRFC-NNNN -
本文(Rust RFC 0000-template 準拠 + 独自 2 節。推奨であって強制ではない — 小さな作業項目は該当なし節を省き Summary / Motivation 中心でよい):
--- state: draft 2026-08-25 review-when: <失効条件(無ければ省略。語は ADR-0044 と同じ review-when)> --- ## Summary ## Motivation ## Guide-level explanation ## Reference-level explanation ## Drawbacks ## Rationale and alternatives ## Prior art ## Unresolved questions ## Future possibilities ## Status ## Next action- 機械契約は 1 つ: 本文の最初の非見出し行(= Summary の 1 行目)が
claims.py readyの 90 字要約になる。frontmatter で機械が読むのはstate:のみ ## Status= state 語 + 現在地の要約 + 日付(IETF「Status of This Memo」型。 state 遷移のたびに更新)。## Next action= 何があれば動くか(blocked の 3 行の家)- 見出しは EN、本文の言語は自由
- 機械契約は 1 つ: 本文の最初の非見出し行(= Summary の 1 行目)が
-
公開規約: 公開が既定 — 本文は公開可能な書き方をし、機微(内部事情・非公開 repo のパス等)はリンク先へ逃がす。公開は撤回不能なので、迷ったら書かない側に倒す
-
接続:
python3 ~/.claude/scripts/claims.py spawn RFC-NNNN --origin <origin>(review 由来は--producer PATH:LINE必須)。着手時はclaim -
index:
rfcs/README.mdの表に 1 行 —| [NNNN](<NNNN-slug>.md) | <title> |の形 (角括弧に番号、丸括弧にファイル名、右列にタイトル)。 state 列は持たない(frontmatter が唯一の正本 — 二重記録は drift する)
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.
- 4d ago Changed · -1 lines c02a05baca5e
- 9d ago First seen · 101 lines · 288 tokens per session scan A a83632c52069
rfc-writer is a skill published in the GitHub repository shimo4228/claude-harness (3 stars, last pushed 4d ago), licensed MIT. It adds 288 tokens to every session and 2,049 once invoked, about $0.0014 per session on Opus 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
agent-adoption-triage
Five-question triage for routing AI work to the right architecture — script, algorithmic search, LLM workflow, or autonomous agentic loop — before any agent is built. Use when someone says "let's build an agent for X", when deciding whether a use case actually needs an autonomous agent, when reviewing an agent…
job-description-skill
A job-description analysis skill that turns a vacancy listing and a candidate’s background into an HTML report about fit, gaps, interview topics, and application strategy.
offer-compare-skill
A decision assistant for comparing two or more job offers across pay, growth, company strength, team risk, promotion, AI exposure, and lifestyle. Total compensation means the combined value of salary, bonuses, shares, and sign-on payments.
offer-toolkit-skill
A set of job-search tools covering the path from finding a vacancy to accepting an offer. It includes separate tools for job searches, job-description analysis, tailored resumes, behavioral interviews, offer comparisons, and salary negotiation.
bq-skill
A coaching workflow for building a reusable library of truthful stories for behavioral job interviews. It uses structures such as STAR—Situation, Task, Action, Result—and can connect stories to a job description and résumé.
linkedin-job-search-skill
A job-search assistant that uses a sample job description and your resume to find and rank similar public LinkedIn Jobs listings. LinkedIn Jobs is LinkedIn’s section for advertised employment positions.