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 skills add harnessworks/harness-starter-kit --skill harnessgit clone --depth 1 https://github.com/harnessworks/harness-starter-kitWrote 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/skills/harnessworks/harness-starter-kit/harness)<a href="https://agentmods.dev/skills/harnessworks/harness-starter-kit/harness"><img src="https://agentmods.dev/badge/skills/harnessworks/harness-starter-kit/harness/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/harnessworks/harness-starter-kit/harness"><img src="https://agentmods.dev/badge/skills/harnessworks/harness-starter-kit/harness.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00048 | $0.00433 |
| Opus 5.5 | $0.00019 | $0.00173 |
| Sonnet 5.5 | $0.00010 | $0.00087 |
| Haiku 4.5 | $0.00005 | $0.00043 |
Grade A, and why
harness 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 1mo 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
Harness
Use this as the command router for Harness Starter Kit workflows.
Steps
- Read
../../references/package-contract.md. - Identify the requested subcommand:
adopt,apply, or no subcommand with an adoption request: read../../references/adopt-workflow.md.doctor: read../../references/doctor-workflow.md.update: read../../references/update-workflow.md.refresh: read../../references/refresh-workflow.md.revieworreview sub-agent: read../../references/review-workflow.md.
- If the target repository has
./harness-starter-kit, prefer the matching canonical workflow doc from that clone over the bundled reference. - Execute the selected workflow exactly according to its mutation boundary: diagnostic workflows inspect and report; adoption and update workflows may edit only when the user asked for that work.
- Finish with the workflow's required report shape. For substantial harness work, say whether task outcome evidence was recorded or skipped and why.
Subcommand Map
| Request | Workflow |
|---|---|
/harness adopt |
Apply prompt-first harness engineering to a target repository. |
/harness doctor |
Score durable harness evidence without modifying files. |
/harness update |
Refresh a target harness from a confirmed kit source. |
/harness refresh |
Review stale, duplicated, obsolete, or unused harness guidance. |
/harness review |
Challenge the current diff from a harness-engineering perspective. |
/harness review sub-agent |
Try the read-only reviewer subagent path, then fall back if unavailable. |
What ships with it
1 file 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.
- 1mo ago First seen · 40 lines · 48 tokens per session scan A 6b4362d86b8d
harness is a skill published in the GitHub repository harnessworks/harness-starter-kit (115 stars, last pushed 4mo ago), licensed MIT. It adds 48 tokens to every session and 433 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-08-30.
Other skills, from other repositories
k-roadmap
A planning skill for discovering, breaking down, and delivering large requirements as a shared, gradual feature map.
k-onboard
A guide for creating a repository’s first verified project map and agent collaboration agreement. A project map explains the codebase, while the agreement records how agents should work in it.
mcore-split-pr
Split a PR into multiple PRs to reduce the number of required CODEOWNERS reviewer groups.
machinist
Use Machinist to create, assign, and monitor software tasks. Use when a coding agent needs to work with Machinist, its GitHub issue workflow, intake labels, direct runs, or managed queue.
project-context-setup
Scaffolds per-repository agent context so coding agents share the same issue tracker rules, triage label vocabulary, domain glossary, ADR layout, and handoff conventions. Triggers on: "set up project context", "configure agent docs", "create CONTEXT.md", "setup agent workflow", "agent issue tracker setup", "triage…
handoff
Hand work to another tool, account or machine and pick it up there, in two words. Use when the user says "hand off", "hand off all", "out of tokens", "switching accounts" or "pick up".