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 browoz/agentic-sdlc-skills --skill agentic-evalsgit clone --depth 1 https://github.com/browoz/agentic-sdlc-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/browoz/agentic-sdlc-skills/agentic-evals)<a href="https://agentmods.dev/skills/browoz/agentic-sdlc-skills/agentic-evals"><img src="https://agentmods.dev/badge/skills/browoz/agentic-sdlc-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/browoz/agentic-sdlc-skills/agentic-evals"><img src="https://agentmods.dev/badge/skills/browoz/agentic-sdlc-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 | $0.00095 | $0.00470 |
| Opus 5 | $0.00048 | $0.00235 |
| Sonnet 5 | $0.00019 | $0.00094 |
| Haiku 4.5 | $0.00010 | $0.00047 |
Grade A, and why
agentic-evals 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 8d 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
Agentic Evals
Use this skill to define how an agentic feature will be judged before treating it as correct. Keep deterministic tests separate from probabilistic evals.
Workflow
- Identify the target:
SPEC.md, existing code, agent behavior, tool contract, or production workflow. - Split behavior into:
- Deterministic: pure logic, schemas, permissions, parsing, API contracts.
- Non-deterministic: planning, tool choice, summaries, ranking, judgment, multi-step recovery.
- For deterministic behavior, write Arrange-Act-Assert test cases and expected failure modes.
- For non-deterministic behavior, define evals across task completion, correctness, efficiency, and safety.
- Use trajectory evals when tool choice, ordering, or recovery path matters.
- Use LLM-as-judge only with a task-specific rubric and a small gold set; prefer pairwise comparison when comparing versions.
- Generate
EVAL_PLAN.mdfromassets/templates/EVAL_PLAN.md.
Gate Design
- Level 1: fast PR checks such as schemas, fixtures, tool contract tests.
- Level 2: deeper nightly or pre-release evals with repeated trials.
- Level 3: deployment gate using acceptance thresholds and manual review for high-impact changes.
References
Read ../agentic-engineering-sdlc/references/day4_security_and_evaluation.md
for deeper evaluation, judge calibration, and trajectory guidance.
Done Criteria
- Success criteria are measurable.
- Deterministic tests and non-deterministic evals are separated.
- Trial count, thresholds, and gold-set source are documented.
- CI gate ownership and failure response are clear.
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.
- 8d ago First seen · 52 lines · 95 tokens per session scan A 795bec5af549
agentic-evals is a skill published in the GitHub repository browoz/agentic-sdlc-skills (3 stars, last pushed 2mo ago), licensed MIT. It adds 95 tokens to every session and 470 once invoked, about $0.0005 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 skills, from other repositories
create-custom-grader
Use when converting an existing benchmark, rubric, verifier, task YAML/JSON, or domain check into SkillEvaluator BYOG/BYOT custom evaluation.
agent-eval
Use when measuring whether an LLM or agent system actually got better and gating merges on it: golden sets, fixing an inflated LLM-as-judge, scoring RAG (faithfulness, contextual recall) or agent trajectories (tool correctness, completion), or picking an eval framework. NOT building the agent loop, tools or RAG…
ai-agent-tool-abuse-and-privilege-escalation
Test AI agent systems for tool abuse, unauthorized actions, privilege escalation through tool chaining, and safety bypass via agentic workflows. Use this skill when assessing autonomous AI agents that use tool-calling (function calling, plugins, actions) to interact with external systems. Covers multi-step attack…
matlab-testing-ci
MATLAB R2026a testing, validation, and CI workflow for matlab.unittest, MATLAB Test, Simulink Test, coverage, artifact generation, GitHub Actions, and open-source reproducibility. Use whenever MATLAB work needs verification, regression tests, CI, GitHub publication, or acceptance criteria.
superpowers
Always-on. The main development method: Plan → TDD → Implement → Verify → Report. Use for ANY non-trivial task. Do not write code without a plan and a test. Complex tasks (>3 files) → split into atomic tasks. Bug fix → Prove-It Pattern (reproduce with a test before the fix).
test-driven-development
Drives development with tests. 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.