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 shipshitdev/skills --skill evaluationgit clone --depth 1 https://github.com/shipshitdev/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/shipshitdev/skills/evaluation)<a href="https://agentmods.dev/skills/shipshitdev/skills/evaluation"><img src="https://agentmods.dev/badge/skills/shipshitdev/skills/evaluation/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/shipshitdev/skills/evaluation"><img src="https://agentmods.dev/badge/skills/shipshitdev/skills/evaluation.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 | $0.00034 | $0.03727 |
| Opus 5.5 | $0.00014 | $0.01491 |
| Sonnet 5.5 | $0.00007 | $0.00745 |
| Haiku 4.5 | $0.00003 | $0.00373 |
Grade A, and why
evaluation 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 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.
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.
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
11 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.
- plugin.json 324 B
- README.md 4.5 KB
- references/judge-bias-mitigation.md 9.0 KB
- references/judge-metrics.md 9.1 KB
- references/judge-patterns.md 8.9 KB
- references/judge-pipeline.md 2.8 KB
- references/judge-prompts.md 4.7 KB
- references/llm-as-judge.md 11 KB
- references/metrics.md 9.9 KB
- scripts/evaluator.py 21 KB runs code
- scripts/llm_judge_example.py 13 KB runs code
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 Changed b009fe8dc0c9
- 13d ago Changed · +18 lines · +7 tokens per session ab8d5f5ffdd5
- 14d ago Changed · +1 lines 099e253a8d03
- 16d ago Changed · +1 lines · +1 tokens per session 2ab6ba400485
- 17d ago Changed eb8d8bc1e61c
- 1mo ago First seen · 290 lines · 26 tokens per session scan A 7dd41d40af8f
evaluation is a skill published in the GitHub repository shipshitdev/skills (38 stars, last pushed yesterday), with no licence file. It adds 34 tokens to every session and 3,727 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
test-driven-development
Drives development with tests using the red-green-refactor loop. Use when implementing any logic, fixing any bug, or changing any behavior. Use when you need to prove that code works, when a bug report arrives, or when you're about to modify existing functionality. Use when asked to add tests to a function, fix a bug…
verification-before-completion
A checklist for verifying work before claiming that it is finished, fixed, built, tested, or ready to submit. It requires fresh command output and evidence for each claim.
test-slack-app
Use when a developer wants to test, try out, smoke-test, verify, or confirm that a Slack app built with the Slack CLI (or a plain Bolt app) actually works, by running it in a developer sandbox or a Free Team, never a workspace with real users, with slack run and exercising its real slash commands, shortcuts, events…
tdd
Test-driven development, from unit to end-to-end tests. Use when the user wants to build features or fix bugs test-first, mentions "red-green-refactor", or wants integration or end-to-end tests (Playwright, Cypress). Don't use to backfill tests on existing code (/refactor) or diagnose an unknown bug (/debug).
awesome-regression-sweep
Read-only sweep for regressions against a recorded baseline: typecheck, lint, test suites, wire contracts, generated-file drift, downstream builds, deploy drift. Use to verify everything before or after a deploy.
awesome-test-writing
Designs and writes tests that catch real regressions: unit, integration or E2E placement, fixtures, behavior-first assertions, characterization and property tests. Use when asked to write tests, add coverage or a regression test.