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 Jamkris/everything-gemini-code --skill eval-harnessgit clone --depth 1 https://github.com/Jamkris/everything-gemini-codeWrote 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/jamkris/everything-gemini-code/eval-harness)<a href="https://agentmods.dev/skills/jamkris/everything-gemini-code/eval-harness"><img src="https://agentmods.dev/badge/skills/jamkris/everything-gemini-code/eval-harness/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/jamkris/everything-gemini-code/eval-harness"><img src="https://agentmods.dev/badge/skills/jamkris/everything-gemini-code/eval-harness.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 | $0.00019 | $0.01351 |
| Opus 5.5 | $0.00008 | $0.00540 |
| Sonnet 5.5 | $0.00004 | $0.00270 |
| Haiku 4.5 | $0.00002 | $0.00135 |
Grade A, and why
eval-harness 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.
This is a copy
78% identical to eval-harness — 33 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 228 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Eval Harness Skill
A formal evaluation framework for Gemini CLI sessions, implementing eval-driven development (EDD) principles.
Philosophy
Eval-Driven Development treats evals as the "unit tests of AI development":
- Define expected behavior BEFORE implementation
- Run evals continuously during development
- Track regressions with each change
- Use pass@k metrics for reliability measurement
Eval Types
Capability Evals
Test if Gemini can do something it couldn't before:
[CAPABILITY EVAL: feature-name]
Task: Description of what Gemini should accomplish
Success Criteria:
- [ ] Criterion 1
- [ ] Criterion 2
- [ ] Criterion 3
Expected Output: Description of expected result
Regression Evals
Ensure changes don't break existing functionality:
[REGRESSION EVAL: feature-name]
Baseline: SHA or checkpoint name
Tests:
- existing-test-1: PASS/FAIL
- existing-test-2: PASS/FAIL
- existing-test-3: PASS/FAIL
Result: X/Y passed (previously Y/Y)
Grader Types
1. Code-Based Grader
Deterministic checks using code:
# Check if file contains expected pattern
grep -q "export function handleAuth" src/auth.ts && echo "PASS" || echo "FAIL"
# Check if tests pass
npm test -- --testPathPattern="auth" && echo "PASS" || echo "FAIL"
# Check if build succeeds
npm run build && echo "PASS" || echo "FAIL"
2. Model-Based Grader
Use Gemini to evaluate open-ended outputs:
[MODEL GRADER PROMPT]
Evaluate the following code change:
1. Does it solve the stated problem?
2. Is it well-structured?
3. Are edge cases handled?
4. Is error handling appropriate?
Score: 1-5 (1=poor, 5=excellent)
Reasoning: [explanation]
3. Human Grader
Flag for manual review:
[HUMAN REVIEW REQUIRED]
Change: Description of what changed
Reason: Why human review is needed
Risk Level: LOW/MEDIUM/HIGH
Metrics
pass@k
"At least one success in k attempts"
- pass@1: First attempt success rate
- pass@3: Success within 3 attempts
- Typical target: pass@3 > 90%
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 First seen · 228 lines · 19 tokens per session scan A 50446c0c4f89
eval-harness is a skill published in the GitHub repository Jamkris/everything-gemini-code (91 stars, last pushed 5mo ago), licensed MIT. It adds 19 tokens to every session and 1,351 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 78% identical to eval-harness, differing in 33 lines, and is treated as a copy.
Other skills, from other repositories
redteam-exploit-validation
Focused workflow for validating exploitability safely and turning candidate issues into reproducible, bounded proof.
onboard-repo
Index an unfamiliar codebase into the knowledge graph, then produce a first orientation map -- entry points, most-depended-upon modules, hotspots, test topology.
refactor-check
Safety analysis before refactoring -- dependency graph, test coverage, public API exposure, blast radius verdict.
test-generation
Generate comprehensive tests for code including unit tests, integration tests, and edge case coverage. Analyzes code to identify testable units and generates tests matching the project's testing framework and conventions.
react-test-engineer
Expert guidance for testing React applications using React Testing Library and Vitest. Focuses on user-centric testing, accessibility, and best practices for unit and integration tests to ensure robust and maintainable code.
bug-investigator
Expert guidance for systematic bug hunting, root-cause analysis, and regression testing. Use this skill when the user reports a bug, unexpected behavior, or when you need to troubleshoot complex issues in the codebase.