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 grahama1970/agent-skills --skill agentic-evalsgit clone --depth 1 https://github.com/grahama1970/agent-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/grahama1970/agent-skills/agentic-evals)<a href="https://agentmods.dev/skills/grahama1970/agent-skills/agentic-evals"><img src="https://agentmods.dev/badge/skills/grahama1970/agent-skills/agentic-evals/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/grahama1970/agent-skills/agentic-evals"><img src="https://agentmods.dev/badge/skills/grahama1970/agent-skills/agentic-evals.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 | $0.00060 | $0.05546 |
| Opus 5.5 | $0.00024 | $0.02218 |
| Sonnet 5.5 | $0.00012 | $0.01109 |
| Haiku 4.5 | $0.00006 | $0.00555 |
Grade A, and why
agentic-evals scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
`evidence_class` is not inferred from a command containing `run.sh` or `curl`. 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
34 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.
- .gitignore 36 B
- DESIGN.md 663 B
- fixtures/agentic_eval.json 26 KB
- fixtures/category_map.example.json 1.9 KB
- fixtures/regressions.json 7.3 KB
- fixtures/runner_selftest.json 11 KB
- fixtures/selftest/blocked_live.json 928 B
- fixtures/selftest/det_only_missing_live.json 1.0 KB
- fixtures/selftest/exemption.json 2.0 KB
- fixtures/selftest/live_proven.json 1.3 KB
- fixtures/selftest/prod.sh 235 B runs code
- fixtures/selftest/pseudo_live.json 843 B
- pyproject.toml 308 B
- README.md 1.1 KB
- REMEDIATION_LOOP.md 18 KB
- run.sh 467 B runs code
- sanity.sh 7.7 KB runs code
- scripts/issue1631_deterministic_proof.py 1.8 KB runs code
- scripts/issue1631_live_e2e.py 9.4 KB runs code
- src/claims.py 12 KB runs code
- src/coverage.py 9.3 KB runs code
- src/domain_profiles.py 5.6 KB runs code
- src/evidence.py 8.6 KB runs code
- src/journeys.py 14 KB runs code
- src/provenance.py 11 KB runs code
- src/regressions.py 9.7 KB runs code
- src/remediation.py 24 KB runs code
- src/runner.py 69 KB runs code
- tests/harden_selftests.sh 7.5 KB runs code
- tests/test_compliance_tier_gate.py 3.2 KB runs code
- tests/test_execution_provenance.py 9.3 KB runs code
- tests/test_journeys.py 6.2 KB runs code
- tests/test_remediation.py 9.6 KB runs code
- uv.lock 15 KB
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 · +8 lines 3b3035e33b09
- 1mo ago Changed · +37 lines 307703c7da0d
- 1mo ago Changed · +22 lines 1eb1b02562e7
- 1mo ago Changed · +6 lines 73fc2a1770ea
- 1mo ago First seen · 415 lines · 60 tokens per session scan A be8ffdf1b26f
agentic-evals is a skill published in the GitHub repository grahama1970/agent-skills (7 stars, last pushed 1mo ago), with no licence file. It adds 60 tokens to every session and 5,546 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
research-engineer
An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.
tika-eval-compare
Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".
cua-driver
Use Cua Driver for desktop or browser tasks that are awkward or unavailable through Bash/APIs, or when the user explicitly wants GUI interaction: app testing, visual bug reproduction, form filling, calendar entry, screenshots, and demo recording. Also covers Cua setup; not OpenAI Codex Computer Use or web research.
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.
atmos-validation
Validate Atmos projects, components, arbitrary JSON Schema inputs, EditorConfig, and GitHub Actions; use affected-file selection and native CI annotations.
skill-benchmark
Benchmark AI skill effectiveness by measuring implementation quality against legacy constraints.