evaluate

A command that sends the current code change to an independent reviewer for scoring against the project's rules.

In plain words
What is it for?
Use it to check a change before finishing a coding task and to receive a pass, warning, or failure result.
Why use it?
It prevents the same agent that made a change from judging its own work. It highlights failures that must be fixed before the task is called complete.

Command

Install

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.

agentmods
npx agentmods add commands/whieet/harness-kit/evaluate
Clone the repo
git clone --depth 1 https://github.com/whieet/harness-kit
Per session 37 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 415 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00037 $0.00415
Opus 5 $0.00018 $0.00208
Sonnet 5 $0.00007 $0.00083
Haiku 4.5 $0.00004 $0.00042

Measured yesterday against content hash e0bab3be9bcc, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 yesterday.

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.

commands/evaluate.md · 23 lines

What it actually says

/harness-kit:evaluate

Run an INDEPENDENT evaluation of the current change — the robust path for Generator/Evaluator separation (a generator grading itself is unreliable).

Steps

  1. Read .harness/config.json first and follow its language preference when relaying the evaluation to the user. Do not translate file/directory names, command names, or config keys.

  2. Dispatch the evaluator subagent (via the Task/Agent tool, subagent type evaluator). It runs with fresh context and has no edit tools, so it cannot grade its own work. Tell it what changed (the current diff scope / the active plan).

  3. The evaluator will: read .harness/rubric.md + config.verificationRecipe, run each dimension's verification check (the project's MCP tools / test runners), score every dimension 1–5 (any dimension < 3 = FAIL), append its scores to .harness/state/trace.jsonl (feeds the config suggester), and return a VERDICT: PASS | WARN | FAIL.

  4. Relay the verdict. On FAIL, list the must-fix items and do not declare the task done — revise and re-evaluate. On WARN, pass but note the technical debt.

Notes

  • This is the recommended, robust evaluator path. An optional experimental auto-fire variant (a type:agent Stop hook) exists in hooks/optional-auto-eval.json — it is context-only (cannot block), runs every Stop, and is off by default; see the README before enabling it.
  • The Stop-hook completion gate (harness-verify + plan DoD) remains the hard, blocking gate; the evaluator is the subjective-quality layer on top.
Changes

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.

  1. yesterday First seen · 23 lines · 37 tokens per session scan A e0bab3be9bcc

Subscribe to this mod's changes

evaluate is a command published in the GitHub repository whieet/harness-kit (5 stars, last pushed 1mo ago), licensed MIT. It adds 37 tokens to every session and 415 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 2026-08-31.