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/harness-mini/harness-mini/evaluatenpx skills add harness-mini/harness-mini --skill evaluategit clone --depth 1 https://github.com/harness-mini/harness-miniWhat 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 | $0.00076 | $0.00943 |
| Opus 5 | $0.00038 | $0.00472 |
| Sonnet 5 | $0.00015 | $0.00189 |
| Haiku 4.5 | $0.00008 | $0.00094 |
Grade A, and why
evaluate 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 — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are grading work against its plan's acceptance criteria — never against vague satisfaction. Agents confidently praise their own work; evaluation exists to break that.
Pick the tier (record it in the plan's eval: field)
"Always spawn an Opus evaluator" is too expensive for every change — if the default is too heavy, people bypass it, and then there is no firewall. So scale rigor with risk. Default is L1.
| Tier | Who grades | Use for | Cost |
|---|---|---|---|
| L0 | builder attaches evidence; main agent runs a compact checklist | tiny, low-risk changes whose criteria are 100% machine-checkable (docs, glue, a one-line fix) | ~free |
| L1 (default) | an independent lightweight reviewer — a fresh context (haiku sub-agent, or a separate prompt/thread on a CLI without sub-agents) | normal slices | low |
| L2 | the full evaluator agent (Opus / strongest available) | cross-slice work, architecture, security, data-loss risk, public-API changes, release gates | high |
When in doubt, go up a tier. L0 is only honest when no criterion needs judgment — the gate is the passing tests, not the builder's opinion. If a criterion needs a human/agent call, it is at least L1.
The firewall is the separate context, not the tooling. No sub-agents available? Run L1/L2 as a fresh prompt/thread with only the criteria + the diff (see
docs/codex-getting-started.md/docs/cursor-getting-started.md).
Procedure (every tier)
- Read the plan's acceptance criteria (from
to-prd). They are the contract. - Verify by interaction, not by reading. Run the tests. Run the app/endpoint where possible. A criterion passes only with evidence you produced — never the builder's claim. (At L0 the "evidence" is the attached test output the main agent re-runs and confirms.)
- For each criterion emit
PASS/FAIL+ the evidence + (on FAIL) the smallest concrete gap. - L1/L2: apply
clean-codeas a secondary lens — cite specific violations.
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 · 72 lines · 76 tokens per session scan A e8220eae51c2
evaluate is a skill published in the GitHub repository harness-mini/harness-mini (2 stars, last pushed 21d ago), licensed MIT. It adds 76 tokens to every session and 943 once invoked, about $0.0004 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
foblex-flow
Authoritative guide for working with Foblex Flow (@foblex/flow) in the skill-map UI. Use whenever editing Angular code in ui/ that touches graph rendering — templates with f-flow / f-canvas / f-connection / fNode / fConnector / fDraggable / fZoom / fMarker directives; TypeScript importing from @foblex/flow…
content-editor
Writes and edits the portfolio's pages. Reads a brief, follows the style guide, and emits the HTML into public/.
notion-publish
Mirrors the portfolio's pages into Notion after publishing, creating one Notion page per site page via the Notion MCP. Use it from /publish, or when the user asks to sync the site to Notion.
check-links
Validates the portfolio's internal links before publishing. Walks every generated page and reports any link whose target is missing.
publish
Publishes the portfolio: runs the link check, hands off to the content editor for any last fixes, then follows the deploy runbook.
master-skill
Example skill paired with the master-agent for the advanced tutorial. Links to the agent so extractors and analyzers have something to chew on.