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/harnessworks/harness-starter-kit/harnessnpx 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.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 | $0.00048 | $0.00433 |
| Opus 5 | $0.00024 | $0.00217 |
| Sonnet 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 6d 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.
- 6d 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 (113 stars, last pushed 2mo ago), licensed MIT. It adds 48 tokens to every session and 433 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
README 文档生成
Use this skill to create or improve README content. Cover what the project does, setup, common commands, configuration, development workflow, and troubleshooting.
API 文档自动生成
根据接口、类型和示例生成结构化 API 文档。.
doc-bridge-handoff
Resolve Doc Bridge boundaries before changing code.
changes
Generate a human-readable explanation of implemented changes after coding. Use after implementing a specification to document what changed, why, which trade-offs were accepted, and which vulnerabilities were found and fixed. The audience includes developers, reviewers, managers, and stakeholders.
init-agents-file
Generate and maintain a repository-specific AGENTS.md file through a conversational interview. Use when setting up project guidelines for coding agents, updating engineering conventions, or configuring team-wide agent behaviour. The generated file reflects the actual architecture, constraints, and conventions of the…
sdd
Transform ideas, tickets, and feature requests into implementation-ready specifications with test cases, methodology, and validation strategy. Use when starting a new feature, clarifying requirements, designing test cases, or documenting architectural decisions before implementation.