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 agents/cantara/kcp-harness/indexgit 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/agents/cantara/kcp-harness/index)<a href="https://agentmods.dev/agents/cantara/kcp-harness/index"><img src="https://agentmods.dev/badge/agents/cantara/kcp-harness/index.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 | $0.00000 | $0.00691 |
| Opus 5 | $0.00000 | $0.00345 |
| Sonnet 5 | $0.00000 | $0.00138 |
| Haiku 4.5 | $0.00000 | $0.00069 |
Grade A, and why
index 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Integrations
KCP Harness works with any MCP-capable AI agent. Each agent has its own config format, rules file, and setup pattern. The kcp-harness integrate command generates the right files for your agent.
Supported Agents
| Agent | Config File | Rules File | Notes |
|---|---|---|---|
| Pi | .pi/mcp.json |
.pi/skills/kcp-harness/SKILL.md |
Project-local MCP and Agent Skills |
| Claude Code | .mcp.json |
CLAUDE.md + hooks |
PreToolUse hooks block ungoverned reads |
| Cursor | .cursor/mcp.json |
.cursor/rules/*.mdc |
Glob-scoped rules with YAML frontmatter |
| GitHub Copilot | .vscode/mcp.json |
.github/copilot-instructions.md |
Uses "servers" key (not "mcpServers") |
| Windsurf | Global config | .windsurfrules |
Global MCP config, not per-project |
| Cline | MCP settings UI | .clinerules |
Auto-approve for read-only tools |
| Continue | .continue/mcpServers/*.yaml |
— | YAML format, directory-based |
| Crush | crush.json |
— | PrepareStep for knowledge pre-loading |
| OpenClaw | openclaw.json |
— | Plugin hooks for prompt injection |
Quick Setup
# Generate integration files for your agent
kcp-harness integrate claude-code
kcp-harness integrate pi
kcp-harness integrate cursor
kcp-harness integrate copilot
# Preview without writing files
kcp-harness integrate claude-code --dry-run
# List all supported agents
kcp-harness integrate --list
# Custom options
kcp-harness integrate cursor \
--manifest ./docs/knowledge.yaml \
--paths "docs/,fragments/"
How It Works
Each integration package generates:
- MCP config — tells the agent where to find the kcp-harness server
- Rules file (if applicable) — instructs the agent to use
kcp_loadfor governed knowledge - Setup instructions — agent-specific steps to complete the integration
The harness itself is the same regardless of agent. The integration layer handles agent-specific config formats and conventions.
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 · 66 lines · 0 tokens per session scan A 00af8e67d98a
index is an agent published in the GitHub repository Cantara/kcp-harness (0 stars, last pushed 10d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 691 tokens. 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
agentic-workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.