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 stellarlinkco/skills --skill harnessgit clone --depth 1 https://github.com/stellarlinkco/skillsWrote 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/stellarlinkco/skills/harness)<a href="https://agentmods.dev/skills/stellarlinkco/skills/harness"><img src="https://agentmods.dev/badge/skills/stellarlinkco/skills/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/stellarlinkco/skills/harness"><img src="https://agentmods.dev/badge/skills/stellarlinkco/skills/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 | $0.00088 | $0.05123 |
| Opus 5 | $0.00044 | $0.02561 |
| Sonnet 5 | $0.00018 | $0.01025 |
| Haiku 4.5 | $0.00009 | $0.00512 |
Grade C, and why
harness scanned grade C with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf "$STALE" Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -sf http://localhost:5432 >/dev/null 2>&1 || echo "WARN: DB not reachable" The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
What ships with it
9 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.
- hooks/_harness_common.py 12 KB runs code
- hooks/harness-claim.py 9.1 KB runs code
- hooks/harness-renew.py 6.7 KB runs code
- hooks/harness-sessionstart.py 5.5 KB runs code
- hooks/harness-stop.py 11 KB runs code
- hooks/harness-subagentstop.py 4.4 KB runs code
- hooks/harness-teammateidle.py 5.0 KB runs code
- hooks/reflect-on-stop.py 7.0 KB runs code
- README.md 7.6 KB
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.
- 12d ago First seen · 373 lines · 88 tokens per session scan C ab525c0d6256
harness is a skill published in the GitHub repository stellarlinkco/skills (26 stars, last pushed 2mo ago), with no licence file. It adds 88 tokens to every session and 5,123 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it C with 2 findings (recursive force delete, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
changelog
Update per-package CHANGELOG.md files for a Ratel release. Drafts entries with git-cliff (scoped per package), lets you curate, then writes the CHANGELOGs. Handles both RC entries and GA-graduation collapse (merging X.Y.Z-rc. sections into a single X.Y.Z section). Invoke before tagging a release.
ops-publish-to-ametyst
Publish local .claude skills/loops to Ametyst — verbatim, flattened, no brain rewrite; optional retire-local (MOVE originals to deprecated-skills/, never delete) makes Ametyst the source of truth.
mk:autobuild
Use when running an autonomous multi-hour build of a green-field product — orchestrates planner → contract → generator ⇄ evaluator loop with adaptive scaffolding density per model tier. Triggers on /mk:autobuild, "build me a kanban app", "build a retro game maker", "autonomous build", or any green-field product spec.…
storozh
Advisory semantic guard over a changeset manifest before it lands in shared state. Use after a multi-repo session produces a changeset-manifest (mirabilis C1) and before the co-sign push gate — classify each unit's routing against the darwin routing-policy (C3) and NLI-check each unit against the shield corpus (claims…
adversarial-review
Run an independent audit gate before any fleet output lands. Use after agent-fleet-orchestration Stage 3 (or any multi-agent build) — before merge, before deploy, before the next phase. Frames the reviewer as an external adversary, not a helper; produces triaged findings with human triage for load-bearing blockers.
robust-by-construction
The engineering invariant bar — what "good" means for systems built by this harness. Use as a checklist during design, as the audit criterion for adversarial-review, and as the source of linter/CI rules to mechanize. Not a style guide; these are correctness and safety properties.