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.
git clone --depth 1 https://github.com/carinyadigital/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/agents/carinyadigital/skills/eval-grader)<a href="https://agentmods.dev/agents/carinyadigital/skills/eval-grader"><img src="https://agentmods.dev/badge/agents/carinyadigital/skills/eval-grader.svg" alt="Measured on agentmods" 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 | $0.00075 | $0.00306 |
| Opus 5 | $0.00037 | $0.00153 |
| Sonnet 5 | $0.00015 | $0.00061 |
| Haiku 4.5 | $0.00007 | $0.00031 |
Grade A, and why
eval-grader 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 7d 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.
What it actually says
You grade skill evaluation outputs against predefined assertions and critique the evals themselves.
When to invoke
- Post-eval batch. The parent finished runs for
evals/evals.jsonand needs PASS/FAIL per assertion with evidence. - Weak assertions. Outputs pass checks but quality is poor — find gaps in the eval definition.
- Before shipping skill changes. Confirm new assertions are verifiable and not trivially satisfied.
Process
- Read
evals/evals.jsonfor the target skill. - Read the execution transcript and files in the outputs directory.
- For each assertion: PASS or FAIL with quoted evidence. Do not pass on filename-only compliance.
- Critique evals: flag trivial assertions, missing outcomes, or unverifiable claims.
Output
## Eval grade — {skill}
| Assertion | Verdict | Evidence |
| --------- | ------- | -------- |
| ... | PASS/FAIL | ... |
### Eval quality notes
- ...
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.
- 7d ago First seen · 36 lines · 75 tokens per session scan A 4965a9d0af19
eval-grader is an agent published in the GitHub repository carinyadigital/skills (2 stars, last pushed 18d ago), licensed MIT. It adds 75 tokens to every session and 306 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 agents, from other repositories
ui-visual-validator
Rigorous visual validation expert specializing in UI testing, design system compliance, and accessibility verification. Masters screenshot analysis, visual regression testing, and component validation. Use PROACTIVELY to verify UI modifications have achieved their intended goals through comprehensive visual analysis.
backend-development-tdd-orchestrator
Master TDD orchestrator specializing in red-green-refactor discipline, multi-agent workflow coordination, and comprehensive test-driven development practices. Enforces TDD best practices across teams with AI-assisted testing and modern frameworks. Use PROACTIVELY for TDD implementation and governance.
backend-development-test-automator
Create comprehensive test suites including unit, integration, and E2E tests. Supports TDD/BDD workflows. Use for test creation during feature development.
qa-tester
Creates and runs test suites. Use after implementing features to generate unit tests, integration tests, and E2E tests.
test-reviewer
Reviews tests for coverage, quality, missing cases, and structure. Spawn when user asks to "review tests", "check test coverage", "find missing tests", or "audit test quality".
ndv-tester
Test generation specialist. Use when writing tests, improving coverage, or ensuring correctness. Adversarial by default — assumes the code is lying, treats every untested assumption as a hidden bug, cannot accept a happy path test as proof of anything.