Install
$ agentstack add mcp-dreamiurg-harness-map ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
harness-map
[](https://github.com/dreamiurg/harness-map/actions/workflows/ci.yml) [](https://codecov.io/gh/dreamiurg/harness-map) [](package.json) [](LICENSE) [](https://skills.sh/dreamiurg/harness-map)
An Agent Skill that generates a self-contained, interactive HTML dependency map of a repository's AI harness: skills, commands, agents, and MCP servers — which skills hand off to which, which agents they delegate to, which MCP servers everything uses.
(Generated from the public obra/superpowers repo — 14 skills, 22 evidence-backed edges, auto-clustered. Interactive version: [examples/superpowers.html](examples/superpowers.html).)
Deterministic scripts scan the repo and build the HTML; the invoking agent does the one thing scripts can't — reading each skill/agent body and inferring typed, evidence-backed dependency edges.
Install
npx skills add dreamiurg/harness-map
This installs the skill to .agents/skills/harness-map/ in your project — the shared location read by Claude Code, Codex, Cursor, and other Agent-Skills-compatible tools.
Or as a Claude Code plugin:
/plugin marketplace add dreamiurg/harness-map /plugin install harness-map@harness-map-marketplace
Use
Ask your agent: "map my AI harness" or invoke /harness-map. Output: harness-map.html (single file, fully offline, open in any browser).
Quickstart for agents
If you are a coding agent (Claude Code, Codex, Cursor, ...) whose human asked you to set this up, do this — verified to work on a clean machine with only Node ≥ 20 and git:
- From the root of the repository you want to map:
npx -y skills add dreamiurg/harness-map -y
The CLI detects agent environments and runs non-interactively. The skill lands in .agents/skills/harness-map/.
- Generate the map now — do not wait for a new session to pick the skill up. Read
.agents/skills/harness-map/SKILL.md and execute its four phases directly: scan (run the script) → infer edges (your judgment; every edge needs a quotable line of evidence) → validate (run the script, fix graph.json until it prints OK) → build (run the script).
- Report to your human: the path to
harness-map.html, node/edge counts, and 2–3
notable findings (orphan skills, the most-depended-on agent, unused MCP servers). Delete harness-map-work/ or gitignore it — only the HTML is the deliverable.
License
MIT
Source & license
This open-source MCP server is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: dreamiurg
- Source: dreamiurg/harness-map
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.