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 chocomyong/harness-kit --skill harness-setupgit clone --depth 1 https://github.com/chocomyong/harness-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/chocomyong/harness-kit/harness-setup)<a href="https://agentmods.dev/skills/chocomyong/harness-kit/harness-setup"><img src="https://agentmods.dev/badge/skills/chocomyong/harness-kit/harness-setup/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/chocomyong/harness-kit/harness-setup"><img src="https://agentmods.dev/badge/skills/chocomyong/harness-kit/harness-setup.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 | $0.00049 | $0.00630 |
| Opus 5.5 | $0.00020 | $0.00252 |
| Sonnet 5.5 | $0.00010 | $0.00126 |
| Haiku 4.5 | $0.00005 | $0.00063 |
Grade C, and why
harness-setup scanned grade C with 2 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
`curl -fsSL https://raw.githubusercontent.com/chocomyong/harness-kit/main/install.sh | sh` Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
`curl -fsSL https://raw.githubusercontent.com/chocomyong/harness-kit/main/install.sh | sh` How it starts
The opening of the file, as written. The whole thing — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Set up harness-kit in this repo
Decide which path applies, then follow only that path.
Which path
- The repo has no rules docs (no AGENTS.md, CLAUDE.md, or house dev guide), or
AGENTS.mdstill contains<PLACEHOLDER>marks -> Fill. - The repo already runs its own rules docs -> Absorb. Never install a second rules system beside an existing one: the same rule stated in two places drifts.
Fill
- If the kit files are not present yet, run the installer from the repo root:
curl -fsSL https://raw.githubusercontent.com/chocomyong/harness-kit/main/install.sh | shIt only adds files and never overwrites. - Read
AGENTS.mdandWORK_PROTOCOL.md. - Survey the repo: file tree,
git log, README and other docs, build and deploy scripts. - Fill every
<PLACEHOLDER>inAGENTS.mdanddocs/REPO_MAP.mdwith measured facts about this repo. Each value comes from something you read here, not from what similar repos look like. - Section 0 (the top invariant) is confirmed by the human. Propose candidates you found - a production datastore, a one-way sync, a paid API - with the file and line that suggested each. Never invent one.
- Keep
AGENTS.mdto rules only and under ~150 lines. Layout and names go todocs/REPO_MAP.md. - Show the full diff and wait for confirmation before saving. Then delete the HTML guidance comments from the filled files.
Absorb
- Read harness-kit's
MINIMAL.mdandprinciples/absence-judgment.md. - Read the repo's existing rules docs end to end.
- Propose the smallest set of edits that folds into the existing docs, in their language and
format:
- the top invariant stated at the top of the highest-authority doc,
- absence-judgment as a named rule,
- an index-first incident registry, seeded with lessons the team keeps re-explaining,
- the three-question done check (ran / fails when wrong / measured in the right place).
- Where a kit idea duplicates one the repo already has, keep theirs and skip the kit's.
- Create no new rule files unless the user agrees. Show the diff before saving.
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 · 50 lines · 49 tokens per session scan C 3384e3a2a8f8
harness-setup is a skill published in the GitHub repository chocomyong/harness-kit (2 stars, last pushed 2d ago), licensed MIT. It adds 49 tokens to every session and 630 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-16.
Other skills, from other repositories
openrig-user
Use when a specific rig command, subcommand, or flag is already known and you need its exact syntax, JSON shape, defaults, or error meaning. NOT for natural capability discovery, open-ended how-do-I questions, or choosing which OpenRig move applies.
applying-a-permission-policy
Use before launching a team during agent-guided setup, or when a user asks to configure OpenRig command permissions, reduce repeated native approval prompts, or apply a selected rig/seat permission policy.
forming-an-openrig-mental-model
Use when the system around you does not make sense yet: you just booted into a seat and do not know how the pieces fit; someone said rig, pod, seat, fleet, topology, or slice and you are not certain what they mean here; you are unsure what kind of rig you are in or what it is for; you do not know how skills reach you…
openrig-software-factory
Use when a user wants a continuing software team for a real repository, or has a first OpenRig team and needs a repeatable path for reviewed work and later tasks.
verification-before-completion
Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always.
agent-starters
Use when creating, refreshing, packaging, inspecting, promoting, or deprecating a named per-seat starting point — Agent Starter manifest authoring, the 6-state lifecycle (captured → named → inspectable → used → promoted → deprecated), provenance honesty, and refusal rules. NOT a VM image; a managed starting point…