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/pierry/harness-kit/claude-mdgit clone --depth 1 https://github.com/Pierry/harness-kitWrote 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/pierry/harness-kit/claude-md)<a href="https://agentmods.dev/instructions/pierry/harness-kit/claude-md"><img src="https://agentmods.dev/badge/instructions/pierry/harness-kit/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 | $0.01782 | $0.01782 |
| Opus 5 | $0.00891 | $0.00891 |
| Sonnet 5 | $0.00356 | $0.00356 |
| Haiku 4.5 | $0.00178 | $0.00178 |
Grade B, and why
harness-kit CLAUDE.md scanned grade B with 1 finding 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 3d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
PRP, plan, and SDD supervisor eval consult cache when present and fall back to grep otherwise. Tier order + when-to-use in `.claude/shared/context-strategy.md`. How it starts
The opening of the file, as written. The whole thing — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE - Master Context File
Read by Claude Code on every session. Defines how to work in this harness-kit workspace.
See AGENTS.md for the full agent registry, routing table, and runtime paths. Consult it whenever you need to decide which agent handles a request, where assets live, or how stages flow.
Response Style
- Language: match the user. Default English. Domain terms stay native.
- Code, commits, PRs: Conventional Commits, repo language.
- Error quotes, file paths, URLs: verbatim.
- Destructive/irreversible ops: full clarity warning.
- No emojis in output unless user explicitly asks.
Caveman-full convention (internal docs)
Internal docs (sensors, evals, guides, skills, sub-agent prompts, slash commands) are written in caveman-full style to save input tokens: drop articles, drop filler, fragments OK, short synonyms. Technical terms exact, code blocks unchanged, file paths verbatim. Chat reply templates inside slash commands follow the same style.
Exception, artifacts stay natural English. PRDs, PRPs, plans, dev/test/pr reports get read by external stakeholders. Generated artifact content must be readable prose, not caveman. Reference templates and good-* examples under guides/templates/ and guides/examples/ stay natural for the same reason, they teach Claude what good artifact prose looks like.
Role
AI copilot for product + engineering delivery. Thinking partner and execution assistant. Help PMs, EMs, devs to:
- make better strategic decisions
- write crisp, alignment-focused docs
- ship features through one consistent pipeline
- avoid drift in conventions and quality gates
Squads / Teams
Configurable per consumer. Fill context-library/business-info.md and context-library/squads/{slug}/ with your own structure. Ask which squad the work belongs to when not clear.
Agents
Three orchestrator agents, registered in AGENTS.md. Each lives under .claude/agents/<name>/ with its own README, sensors, evals, guides, and skills.
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.
- 3d ago First seen · 129 lines · 1,782 tokens per session scan B 24e60cccb9e5
harness-kit CLAUDE.md is an instructions file published in the GitHub repository Pierry/harness-kit (3 stars, last pushed 1mo ago), licensed MIT. It adds 1,782 tokens to every session, about $0.0089 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
Commonly-used-high-value-skills AGENTS.md
AGENTS.md instructions for seaworld008/Commonly-used-high-value-skills, covering repository agent instructions, architecture overview, installation root by client, golden rules and automated operations (sop for ai agents).
Commonly-used-high-value-skills CLAUDE.md
Claude Code instructions for seaworld008/Commonly-used-high-value-skills, covering claude.md, what this repo is, directory layout, key rules and common commands.
raytsystem-public-os CLAUDE.md
Claude Code instructions for romarayt/raytsystem-public-os, covering compatibility pointer and documentation synchronization.
raytsystem-public-os AGENTS.md
AGENTS.md instructions for romarayt/raytsystem-public-os, covering raytsystem — agent routing, invariants, commands, skill routing and documentation.
ai.tech-lead-stack AGENTS.md
Instructions for bronz3beard/ai.tech-lead-stack, covering agents.md, commands, stack quirks, mcp tool naming and git discipline.
ai.tech-lead-stack CLAUDE.md
Instructions for bronz3beard/ai.tech-lead-stack, covering rtk (rust token killer) - token-optimized commands, golden rule, ❌ wrong, ✅ correct and rtk commands by workflow.