skill-harness CLAUDE.md

skill-harness CLAUDE.md is an instructions file for coding agents from 45ck/skill-harness. It costs 958 tokens per session, scanned A, original, MIT.

Maintainer instructions for Skill Harness, a project that packages reusable coding-agent skills and developer documentation. They require software changes to be reflected in suitable UML, C4, or other model records when relevant.

In plain words
What is it for?
Use them when changing code, APIs, workflows, dependencies, deployment, user-interface structure, or agent behaviour in the Skill Harness project.
Why use it?
They give contributors consistent rules for choosing specialist agents, managing project models, and contributing safely through the documented workflow.

Instructions file

Install

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.

agentmods
npx agentmods add instructions/45ck/skill-harness/claude-md
Clone the repo
git clone --depth 1 https://github.com/45ck/skill-harness

Wrote 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.

agentmods badge for skill-harness CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/45ck/skill-harness/claude-md.svg)](https://agentmods.dev/instructions/45ck/skill-harness/claude-md)
Your own site
<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>
Per session 958 This file is loaded in full into every session.
When invoked 958 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 4d ago against content hash d71314cbe920, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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.

CLAUDE.md · 38 lines

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 to uml-first for new repos and preserves existing repos. Use --modeling-mode off|baseline|uml-first or --skip-modeling only 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.md and docs/artifacts/artifacts.manifest.json current 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 with node scripts/generate-model-review.mjs; validate with node scripts/check-model-artifact-policy.mjs and node 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 entry reviewRequired: true, generate with node 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.mjs to open the system default browser or print the file URL in headless/CI contexts.
  • Use node scripts/open-artifact-review.mjs --json --print when 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.

Read the full file on GitHub · 38 lines

Changes

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.

  1. 4d ago First seen · 38 lines · 958 tokens per session scan A d71314cbe920

Subscribe to this mod's changes

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.