Borrowing it
Nothing to install: this file belongs to Cantara/kcp-harness. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Cantara/kcp-harness/main/CLAUDE.mdgit clone --depth 1 https://github.com/Cantara/kcp-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/cantara/kcp-harness/claude-md)<a href="https://agentmods.dev/instructions/cantara/kcp-harness/claude-md"><img src="https://agentmods.dev/badge/instructions/cantara/kcp-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 5.1 | $0.00407 | $0.00407 |
| Opus 5 | $0.00204 | $0.00204 |
| Sonnet 5 | $0.00081 | $0.00081 |
| Haiku 4.5 | $0.00041 | $0.00041 |
Grade A, and why
kcp-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 7d 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
kcp-harness
MCP compliance proxy: routes an AI agent's knowledge-related tool calls through the kcp-agent deterministic planner (14-gate cascade, no LLM), producing decision traces, audit logs, and budget ledgers as a side effect of normal agent operation. Ships as an npm package plus native binaries, with integration generators for Claude Code, Cursor, Copilot, and others.
Start here
knowledge.yaml is this repo's canonical, agent-navigable source of truth (signed via
knowledge.yaml.sig; the repo dogfoods its own governance through harness.yaml). Query it
before grepping: npx kcp-agent plan "how does the harness govern a tool call?" --manifest .
Skills
Governed-skill authoring conventions (envelope shape, action_scope as a firewall rule) live in
Cantara/kcp-skill PROFILE.md — read before writing or
reviewing any kind: skill unit here. This repo's own skills/ holds procedures specific to
operating kcp-harness (shared library content is federated from kcp-skill, never copied):
cut-a-release— the two-workflow release handoff (release.yml→ci.yml)resign-knowledge-yaml— recover an invalidatedknowledge.yaml.sigon a PR branch
Gotchas
- Editing
knowledge.yamlinvalidatesknowledge.yaml.sig; CI checks it on the PR itself, so merging tomainwon't fix an already-red check. - Releases aren't a plain
git tag && push— seeskills/cut-a-release/first. - Raw NUL bytes break node/bun parity (issue #51);
scripts/check-nul-bytes.shenforces this.
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.
- 7d ago First seen · 30 lines · 407 tokens per session scan A d2990c48cec1
kcp-harness CLAUDE.md is an instructions file published in the GitHub repository Cantara/kcp-harness (0 stars, last pushed 13d ago), licensed Apache-2.0. It adds 407 tokens to every session, about $0.0020 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
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.