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 easyinplay/harnessed --skill eval-reviewgit clone --depth 1 https://github.com/easyinplay/harnessedWrote 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/easyinplay/harnessed/eval-review)<a href="https://agentmods.dev/skills/easyinplay/harnessed/eval-review"><img src="https://agentmods.dev/badge/skills/easyinplay/harnessed/eval-review/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/easyinplay/harnessed/eval-review"><img src="https://agentmods.dev/badge/skills/easyinplay/harnessed/eval-review.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 | $0.00116 | $0.01374 |
| Opus 5.5 | $0.00046 | $0.00550 |
| Sonnet 5.5 | $0.00023 | $0.00275 |
| Haiku 4.5 | $0.00012 | $0.00137 |
Grade A, and why
verify-eval-review 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 1mo 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
verify-eval-review workflow (v3)
Overview
1-phase sub-workflow auditing AI phase eval coverage (v13.0 P42 upstream re-sync — D-04
Stage ④ Verify conditional sub + GSD eval-review wire)。Pairs with the plan-side
gsd-ai-integration-phase (AI-SPEC.md eval strategy): verify 侧回查实现是否真覆盖规划的
eval 维度,产出 EVAL-REVIEW.md (逐维度 COVERED/PARTIAL/MISSING)。
| phase | id | upstream | model | capability | gate |
|---|---|---|---|---|---|
| 1 | 01-eval-review |
gsd | sonnet | {{ capabilities.gsd-eval-review.cmd }} |
judgments.stage-routing.verify-eval-review-aiphase.fires |
Per-phase config loads from workflows/verify/eval-review/workflow.yaml; engine 4-level gate
resolver evaluates phase.has_ai_phase == true via expr-eval — true 则 invoke GSD
/gsd-eval-review (eval 覆盖审计 → EVAL-REVIEW.md), false 则 skip。
Capability refs
Sister workflows/capabilities.yaml entries:
gsd-eval-review— Bucket 2 special-purpose (impl: gsd, cmd: /gsd-eval-review, fires_when: has_ai_phase)
Gate ref
Sister workflows/judgments/stage-routing.yaml:
verify-eval-review-aiphase.fires—phase.stage == 'verify' and phase.has_ai_phase == true
How to invoke
!harnessed checkpoint intent verify-eval-review
The banner above (when present) means this invocation is REGISTERED with the engine (an intent marker) — not yet compliant: the steps below (prompt → spawn → checkpoint complete) resolve it, and a per-turn
<workflow-intent>reminder persists until they run.
The numbered sequence below is the state machine — execute it with Bash. Do NOT improvise an equivalent flow from the Overview above: freelancing bypasses the engine (no ledger, no evidence guard). harnessed gives you the spawn-ready prompt; YOU spawn the subagent with a {{ host.native }} {{ host.spawn_subagent }} (keeps the session responsive + lets clarification round-trips reach the user).
Do NOT pipe to harnessed run verify-eval-review — that is the CI/headless path ({{ host.harnessed_run_warning_note.execution_tail }}
What ships with it
2 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.
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.
- 1mo ago Changed · -1 lines 74ccb8975a5d
- 2mo ago First seen · 77 lines · 116 tokens per session scan A 79c86882345f
verify-eval-review is a skill published in the GitHub repository easyinplay/harnessed (2 stars, last pushed yesterday), licensed Apache-2.0. It adds 116 tokens to every session and 1,374 once invoked, about $0.0005 per session on Opus 5.5. 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
prompt-testing
Use when comparing two prompt variants, defining quality/efficiency/robustness metrics, or deciding whether to adopt a challenger prompt over a baseline.
harness:health
Use when the user wants to check dataset quality, diagnose eval issues, or before running evolve. Checks size, difficulty distribution, dead examples, coverage, and splits. Auto-corrects issues found.
review-testing
Review test code for quality, design, and completeness after implementing a feature or fixing a bug. Use when the user asks to "review my tests", "check my test quality", "are these tests good enough", "review testing", or after completing a feature implementation that includes tests. Also use when tests feel brittle…
prompt-regression-suite
Design a regression test suite that catches an LLM feature getting worse when the prompt, model, or context changes. Use when asked to stop prompt changes breaking production, set up golden tests or CI gates for an LLM feature, or test a model/prompt upgrade before shipping it. Produces a golden case set, per-case…
lab:autoresearch
Self-improving loop for plugin skills. Reads program.md, proposes one mutation per iteration, evaluates against deterministic scorer, keeps improvements via git, reverts failures. Targets weakest skill+dimension. Use with /loop for overnight runs.
verify
Verify Elixir/Phoenix changes — compile, format, and test in one loop. Use after implementation, before PRs, or after fixing bugs.