harness-kit CLAUDE.md

harness-kit CLAUDE.md is an instructions file for coding agents from Pierry/harness-kit. It costs 1,782 tokens per session, scanned B, original, MIT.

A set of workspace instructions for Pierry and harness-kit, including the main Claude context file, agent roles, routing, and team workflows. It also defines language and formatting conventions for internal and external documents.

In plain words
What is it for?
Use it to guide work in the harness-kit workspace, select agents and workflow stages, follow repository conventions, and distinguish concise internal notes from readable project artifacts.
Why use it?
It gives agents shared rules for locating resources, choosing the right role, and presenting work consistently. This reduces confusion across multi-agent projects.

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/pierry/harness-kit/claude-md
Clone the repo
git clone --depth 1 https://github.com/Pierry/harness-kit

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 harness-kit CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/pierry/harness-kit/claude-md.svg)](https://agentmods.dev/instructions/pierry/harness-kit/claude-md)
Your own site
<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>
Per session 1,782 This file is loaded in full into every session.
When invoked 1,782 The same file — it is already loaded in full.
Security scan B 1 finding. 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 $0.01782 $0.01782
Opus 5 $0.00891 $0.00891
Sonnet 5 $0.00356 $0.00356
Haiku 4.5 $0.00178 $0.00178

Measured 3d ago against content hash 24e60cccb9e5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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`.
CLAUDE.md · 129 lines

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.

Read the full file on GitHub · 129 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. 3d ago First seen · 129 lines · 1,782 tokens per session scan B 24e60cccb9e5

Subscribe to this mod's changes

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.

Related

Other instructions, from other repositories