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/45ck/skill-harness/claude-mdgit clone --depth 1 https://github.com/45ck/skill-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/45ck/skill-harness/claude-md)<a href="https://agentmods.dev/instructions/45ck/skill-harness/claude-md"><img src="https://agentmods.dev/badge/instructions/45ck/skill-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 | $0.00958 | $0.00958 |
| Opus 5 | $0.00479 | $0.00479 |
| Sonnet 5 | $0.00192 | $0.00192 |
| Haiku 4.5 | $0.00096 | $0.00096 |
Grade A, and why
skill-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.
How it starts
The opening of the file, as written. The whole thing — 38 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill Harness
Use the narrowest specialist agent that can own the work end to end. Treat this repo as the suite entrypoint and project setup repo for the 45ck stack, including embedded packs under packs/.
This is maintainer and agent operating guidance. Public contributors should start with CONTRIBUTING.md, SUPPORT.md, and SECURITY.md; fork-based contributors do not need Beads locally and should use pull requests instead of direct pushes.
UML-First Developer Artifacts
- Auto-detect model impact for every engineering change. When code, API, workflow, dependency, deployment, UI structure, or agent behavior changes, update the relevant model source or record why no model change is needed.
- Fresh developer-artifact setups use
--modeling-mode auto, which resolves touml-firstfor new repos and preserves existing repos. Use--modeling-mode off|baseline|uml-firstor--skip-modelingonly when that is intentional. - Keep canonical UML/UWE/C4/evidence model sources in repo-relative text files. Prefer
docs/artifacts/source/models/when no better domain docs path exists. - Keep
docs/artifacts/source/models/model-inventory.mdanddocs/artifacts/artifacts.manifest.jsoncurrent with model ids, owners, methods, source paths, evidence, and generated review surfaces. - Human model artifacts belong in static HTML under
generated/review/models/. Generate them withnode scripts/generate-model-review.mjs; validate withnode scripts/check-model-artifact-policy.mjsandnode scripts/check-artifact-html-policy.mjs. - Human-facing discovery, planning, research, product, business, data, and UX artifacts belong in source-backed infographic HTML under
generated/review/<family>/. Create the canonical source first, mark the manifest entryreviewRequired: true, generate withnode scripts/generate-artifact-review.mjs, then surface/open the HTML review page. - Default generated review interaction is CSS-only: radio tabs, details/summary, anchor navigation, and inline SVG states. Do not add inline JavaScript; the reviewed inline-JS lane is reserved until manifest-aware checker and CSP support are implemented.
- Open generated HTML in the best available human review surface. In Codex app, prefer the Browser plugin for local HTML. In Claude desktop, prefer the built-in browser or preview. In CLI-only contexts, use
node scripts/open-artifact-review.mjsto open the system default browser or print the file URL in headless/CI contexts. - Use
node scripts/open-artifact-review.mjs --json --printwhen a host workflow needs the resolved review target and preferred open action before choosing a browser, preview, or local HTTP fallback. - Treat generated HTML, SVG, PNG, screenshots, and comparison pages as review surfaces only. Canonical truth stays in source artifacts and model diffs.
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 · 38 lines · 958 tokens per session scan A d71314cbe920
skill-harness CLAUDE.md is an instructions file published in the GitHub repository 45ck/skill-harness (15 stars, last pushed 2mo ago), licensed MIT. It adds 958 tokens to every session, about $0.0048 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 2026-08-30.
Other instructions, from other repositories
apm python.instructions.md
Python development guidelines.
CodexPotter AGENTS.md
AGENTS.md instructions for breezewish/CodexPotter, covering repository guidelines, workflow principles, engineering rules, core principles: simplicity & readability and better maintainability.
OpenMicro AGENTS.md
Instructions for stephenleo/OpenMicro, covering openmicro — project conventions and releases.
squarebox CLAUDE.md
Instructions for SquareWaveSystems/squarebox, covering claude.md, agent skills, issue tracker, triage labels and domain docs.
codmate AGENTS.md
Instructions for loocor/codmate, a project described as: CodMate is a macOS SwiftUI app for managing CLI AI sessions: browse, search, organize, resume, and review work produced by Codex, Claude Code, and Gemini CLI. It focuses on speed, a compact three-column UI, and “ship it” workflows like Project Review (Git…
CodexBar AGENTS.md
AGENTS.md instructions for bob-zebedy/CodexBar, covering repository guidelines, 项目结构与模块组织, 构建、测试与开发命令, 写作风格 and 代码和注释.