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 harness-boundarygit 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/harness-boundary)<a href="https://agentmods.dev/skills/shimo4228/claude-harness/harness-boundary"><img src="https://agentmods.dev/badge/skills/shimo4228/claude-harness/harness-boundary/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/harness-boundary"><img src="https://agentmods.dev/badge/skills/shimo4228/claude-harness/harness-boundary.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 | $0.00372 | $0.02866 |
| Opus 5 | $0.00186 | $0.01433 |
| Sonnet 5 | $0.00074 | $0.00573 |
| Haiku 4.5 | $0.00037 | $0.00287 |
Grade A, and why
harness-boundary 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 10d 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 — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
harness-boundary — harness を捨てても残るものだけを資産にする設計レンズ
「ハーネスこそ資産」は半分しか正しくない。モデル固有の弱点を補う harness logic は モデル世代ごとに陳腐化し、runtime（tool 実行・permission・state・retry・agent loop）は 標準化と置換が進む。残るのは harness の中に混在している別の層だ。この skill は mechanism を追加・変更・レビューするときに、その混在を分解するための問いを出す。
これは architecture の強制ではなく、資産境界・可搬性・陳腐化を判断するレンズである。
中心原則
- Model capability はモデルに置く。harness で再実装しない
- Procedural knowledge は skill に置く
- Values と責任境界は明示的で検査可能な形に保つ
- Quality の定義は eval に置く
- Domain 知識と履歴は data / memory に置く
- Runtime は実用上できる限り薄く、交換可能に保つ
そして: harness を保存するために最適化しない。harness を交換しても残るべきものを 保存するために最適化する。 新しいモデルが既存 logic を不要にしたなら、それは設計の 失敗ではなく削除のタイミングである。Delete / Simplify は成功として扱う。
6 層
| 層 | 中身 | この harness での対応物 | 既存語彙 |
|---|---|---|---|
| Model capability | reasoning / planning / coding / tool-use 判断 / self-correction / decomposition / reflection | Claude 本体（system prompt + tool description を含む） | substrate、generation-audit の runtime 層 |
| Skills（手続き記憶） | この task はこの手順 / このレビューはこの観点 / この障害はこの runbook / この成果物はこの検証 | skills/*/SKILL.md、agents/*.md の本文 |
「手順は skill」（rules/README.md） |
| Values / Policies / 責任境界 | 何を優先するか / 何をしないか / 人間承認が要る操作 / 委譲範囲 / 正本 / 失敗時の優先 | rules/common/（identity / values 層、ADR-0018 D7）、settings.json の permissions、task request の権限 |
「環境固有の事実・配線・罠」（ADR-0035） |
| Evals | acceptance criteria / tests / rubric / benchmark / regression / quality gate | .claude/verify.sh、tests/、skill-comply、llm-as-judge、judge agent（readme-judge 等） |
Verify、binding 判定 |
| Data / Memory | 成果物 / decision history / domain 知識 / preferences / provenance / 履歴状態 | docs/adr/、auto-memory、.notes/、metrics/*.jsonl、wiki |
ADR = 日付つき仮説 |
| Runtime | tool calling / shell・fs / permission 実装 / sandbox / connector / retry / logging / state / routing / agent loop | Claude Code 本体、hooks/*.sh、MCP server、Workflow / Agent tool、launchd tick |
control plane（ADR-0019）、hook は時刻（ADR-0035） |
hooks は runtime 層に座るが、policy を黙って encode しやすい（例: 承認 gate の条件、 何を block するか）。hook を見るときは「時刻の配線」と「中に埋まった policy」を分けて、 後者は rule / ADR に見える形で出ているかを問う。
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.
- 10d ago First seen · 130 lines · 372 tokens per session scan A e3489dad06ad
harness-boundary is a skill published in the GitHub repository shimo4228/claude-harness (3 stars, last pushed 4d ago), licensed MIT. It adds 372 tokens to every session and 2,866 once invoked, about $0.0019 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.