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 skills/harnessprotocol/harness-kit/harness-docsnpx skills add harnessprotocol/harness-kit --skill harness-docsgit clone --depth 1 https://github.com/harnessprotocol/harness-kitWhat 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 | $0.00097 | $0.00929 |
| Opus 5 | $0.00048 | $0.00464 |
| Sonnet 5 | $0.00019 | $0.00186 |
| Haiku 4.5 | $0.00010 | $0.00093 |
Grade A, and why
harness-docs 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 2d 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Harness Kit Documentation
harness-kit is a harness-agnostic framework for AI coding tools. Plugins, skills, MCP servers, hooks, and conventions live in one portable config. It works with Claude Code today and is designed to travel across tools.
Repo: https://github.com/harnessprotocol/harness-kit
Docs: https://harnesskit.ai/docs
How to Use This Skill
This is a background knowledge skill. When the user asks about harness-kit, load the relevant reference file from ${CLAUDE_SKILL_DIR}/references/ and answer from it.
| Topic | Reference file |
|---|---|
| Installation, architecture, quick start | getting-started.md |
| Plugin list, what each plugin does | plugin-catalog.md |
| Creating plugins, writing SKILL.md, frontmatter | creating-plugins.md |
| Using with Copilot, Cursor, Codex | cross-harness.md |
| Core concepts, FAQ, harness.yaml, comparison with MCP/A2A | concepts-and-faq.md |
Load with: Read ${CLAUDE_SKILL_DIR}/references/<filename>.md
Quick Reference: 17 Plugins
| Plugin | Slash command | What it does |
|---|---|---|
| research | /research |
Process any source (URL, GitHub, YouTube, PDF) into a structured knowledge base |
| orient | /orient |
Topic-focused session orientation across knowledge graph and research |
| capture | /capture |
Capture session info into a staging file for later reflection |
| review | /review |
Structured code review for branches, PRs, or file paths with severity labels |
| rubber-ducky | /rubber-ducky |
Second opinion on a plan, design, or diff — independent critics on different Claude models |
| explain | /explain |
Layered explanations of files, functions, directories, or concepts |
| lineage | /lineage |
Column-level lineage tracing through SQL, Kafka, Spark, JDBC |
| docgen | /docgen |
Generate or update README, API docs, architecture overview, or changelog |
| open-pr | /open-pr |
Pre-flight checks and PR creation: tests, review, CI |
| merge-pr | /merge-pr |
Merge a ready PR: verify CI, sync base, squash merge, clean up |
| pr-sweep | /pr-sweep |
Cross-repo PR sweep: triage, review, merge, fix CI |
| dependabot-sweep | /dependabot-sweep |
End-to-end Dependabot remediation: fetch alerts, fix per ecosystem, verify, open/merge a PR |
| harness-share | /harness-export, /harness-import |
Compile, export, import, and sync harness configs across 8 AI coding tools |
| stats | /stats |
Interactive HTML dashboard for Claude Code token and session usage |
| iterm-notify | — | macOS desktop notifications and iTerm2 badge management for Claude Code events |
| frontend-design | /frontend-design |
Production-grade frontend design rules: OKLCH color, typography, motion, accessibility |
| membrain | /memory |
Graph-based agent memory — search, trace, and manage a persistent knowledge graph |
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2d ago First seen · 63 lines · 97 tokens per session scan A 52949a997fd7
harness-docs is a skill published in the GitHub repository harnessprotocol/harness-kit (10 stars, last pushed 3d ago), licensed Apache-2.0. It adds 97 tokens to every session and 929 once invoked, about $0.0005 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 skills, from other repositories
studio
Architecture Studio control plane — initialize or inspect a studio workspace, create and register projects, or route an architecture/AEC task to the right agent or skill. Use when the user runs /as:studio, asks to set up or open their studio, manage its projects, or describes a task without naming a skill.
epd-to-spec
Write CSI specification language for EPD submittals and sourced GWP limits. Use to add embodied-carbon or EPD requirements to specs; not to parse, find, or compare EPDs.
occupancy-calculator
Calculate code occupant loads by area with gross/net factors and jurisdiction checks. Use for "how many people can this space hold," IBC Table 1004.5, egress inputs, or occupancy-load reports; not for workplace headcount planning.
workplace-programmer
Build office space programs through guided workplace strategy: area splits, room schedules, and planned seat counts. Use to program or size a workplace; not for code occupant-load calculations.
workplan
Create a durable, execution-ready work plan for repository changes, operations, research, or AEC project delivery. Use when the user asks to plan, scope, sequence, coordinate, or break down multi-step work before acting. Do not use for floor plans, site plans, space planning, zoning calculations, building-code…
zoning-analysis-nyc
Analyze NYC lot zoning, FAR, height, setbacks, uses, and buildable envelope from PLUTO and the Zoning Resolution. Use for "what can I build"; use nyc-bsa for relief and zoning-envelope for 3D visualization.