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 agentmods add instructions/dotoricode/tink-harness/claude-mdgit clone --depth 1 https://github.com/dotoricode/tink-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/instructions/dotoricode/tink-harness/claude-md)<a href="https://agentmods.dev/instructions/dotoricode/tink-harness/claude-md"><img src="https://agentmods.dev/badge/instructions/dotoricode/tink-harness/claude-md.svg" alt="Measured on agentmods" 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 | $0.00363 | $0.00363 |
| Opus 5 | $0.00181 | $0.00181 |
| Sonnet 5 | $0.00073 | $0.00073 |
| Haiku 4.5 | $0.00036 | $0.00036 |
Grade A, and why
tink-harness CLAUDE.md 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.
What it actually says
tink-harness
Claude Code용 하네스 관리자. 용어 정의는 CONTEXT.md 참고.
명령
npm test # python tests/test_templates.py && node --check bin/install.js
npm publish # npm 배포 (.npmrc 토큰 필요)
구조
bin/install.js # npx 진입점 (install / update 서브커맨드)
commands/*.md # 소스 명령 파일 (plugin용)
templates/claude/commands/tink/ # npx 설치 시 복사되는 명령 파일
templates/tink/harnesses/ # npx 설치 시 복사되는 하네스 파일
.claude/commands/tink/ # 이 repo에서 직접 사용하는 명령 파일
.tink/ # Tink 런타임 상태 (로컬 전용, git 제외)
3-copy 규칙
commands/*.md 수정 시 반드시 세 곳 모두 동일하게 적용:
commands/<name>.mdtemplates/claude/commands/tink/<name>.md.claude/commands/tink/<name>.md
버전 bump
package.json, package-lock.json, .claude-plugin/plugin.json 세 곳 모두 수정 필요.
주의
- Windows cp949 환경에서 테스트 실행 시 UnicodeDecodeError 경고 발생 — 기존 이슈, 테스트 통과에 영향 없음
ROADMAP.md는 커밋하지 않음.npmrc는.gitignore에 포함됨 (토큰 보안)npm pkg fix --dry-run은 실제로 파일을 수정함 (dry-run 미작동)
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 First seen · 41 lines · 363 tokens per session scan A 180476e22f6d
tink-harness CLAUDE.md is an instructions file published in the GitHub repository dotoricode/tink-harness (1 stars, last pushed 1mo ago), licensed MIT. It adds 363 tokens to every session, about $0.0018 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 instructions, from other repositories
ai-harness CLAUDE.md
Claude Code instructions for samartomar/ai-harness, covering ai-harness — claude bootloader, vocabulary — two different things, read the source, not a summary of it, start here and self-hosting boundary.
ai-harness AGENTS.md
AGENTS.md instructions for samartomar/ai-harness, covering ai-harness — agent bootloader (agents.md), start here, self-hosting boundary, working agreement and invariants.
AmbyKit CLAUDE.md
Instructions for ambystechcom/AmbyKit, covering claude code — notes for the ambykit repo and claude-specific.
ai-auto-work CLAUDE.md
Claude Code instructions for chaohong-ai/ai-auto-work, covering gamemaker - ai native 游戏创作平台, 项目简介, ai 工作目录约定 and 按需加载（不默认装载）.
catalyst AGENTS.md
AGENTS.md instructions for coalesce-labs/catalyst, covering agents.md, what this repository is, agent philosophy, build & test and key principles.
better-codebase CLAUDE.md
Claude Code instructions for NicolasYusim/better-codebase: Read and follow AGENTS.md when developing this repository.