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 autohandai/community-skills --skill agent-evaluationgit clone --depth 1 https://github.com/autohandai/community-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/autohandai/community-skills/agent-evaluation)<a href="https://agentmods.dev/skills/autohandai/community-skills/agent-evaluation"><img src="https://agentmods.dev/badge/skills/autohandai/community-skills/agent-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/autohandai/community-skills/agent-evaluation"><img src="https://agentmods.dev/badge/skills/autohandai/community-skills/agent-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 | $0.00049 | $0.03361 |
| Opus 5 | $0.00024 | $0.01681 |
| Sonnet 5 | $0.00010 | $0.00672 |
| Haiku 4.5 | $0.00005 | $0.00336 |
Grade A, and why
agent-evaluation 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 10d 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
result = subprocess.run( How it starts
The opening of the file, as written. The whole thing — 484 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Evaluation (AI Agent Evals)
Based on Anthropic's "Demystifying evals for AI agents"
When to use this skill
- Designing evaluation systems for AI agents
- Building benchmarks for coding, conversational, or research agents
- Creating graders (code-based, model-based, human)
- Implementing production monitoring for AI systems
- Setting up CI/CD pipelines with automated evals
- Debugging agent performance issues
- Measuring agent improvement over time
Core Concepts
Eval Evolution: Single-turn → Multi-turn → Agentic
| Type | Turns | State | Grading | Complexity |
|---|---|---|---|---|
| Single-turn | 1 | None | Simple | Low |
| Multi-turn | N | Conversation | Per-turn | Medium |
| Agentic | N | World + History | Outcome | High |
7 Key Terms
| Term | Definition |
|---|---|
| Task | Single test case (prompt + expected outcome) |
| Trial | One agent run on a task |
| Grader | Scoring function (code/model/human) |
| Transcript | Full record of agent actions |
| Outcome | Final state for grading |
| Harness | Infrastructure running evals |
| Suite | Collection of related tasks |
Instructions
Step 1: Understand Grader Types
Code-based Graders (Recommended for Coding Agents)
- Pros: Fast, objective, reproducible
- Cons: Requires clear success criteria
- Best for: Coding agents, structured outputs
# Example: Code-based grader
def grade_task(outcome: dict) -> float:
"""Grade coding task by test passage."""
tests_passed = outcome.get("tests_passed", 0)
total_tests = outcome.get("total_tests", 1)
return tests_passed / total_tests
# SWE-bench style grader
def grade_swe_bench(repo_path: str, test_spec: dict) -> bool:
"""Run tests and check if patch resolves issue."""
result = subprocess.run(
["pytest", test_spec["test_file"]],
cwd=repo_path,
capture_output=True
)
return result.returncode == 0
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.
- 10d ago First seen · 484 lines · 49 tokens per session scan A 4c98974f8938
agent-evaluation is a skill published in the GitHub repository autohandai/community-skills (11 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 49 tokens to every session and 3,361 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
dataset-evaluation
Validates dataset formatting and quality for SageMaker model fine-tuning (SFT, DPO, or RLVR). Use when the user says "is my dataset okay", "evaluate my data", "check my training data", "I have my own data", or before starting any fine-tuning job. Detects file format, checks schema compliance against the selected model…
agentsop-domain-eval-set
Build and govern a 50-200 example domain-specific held-out benchmark sampled from real traffic. Distinct from public benchmarks (MMLU/HumanEval/GSM8K via lm-evaluation-harness) which measure GENERAL capability. Only a held-out domain set predicts whether THIS system works on YOUR data. Collect real examples, label…
agentsop-regression-gate
Build a held-out eval set, run it on every prompt/model change, and block regressions in CI. An LM change is a code change — gate it with a test suite (eval set + metric + threshold). Cross-framework SOP not surfaced by any single base skill.
agentsop-test-fix-loop
Decision protocol for wiring a verify-then-fix loop around a code-editing LLM agent. The agent edits → runs lint/test → reads the output → fixes → re-runs, bounded by an iteration cap and an escalation rule. Activates whenever a coder agent has a verifiable success criterion (exit code, type-checker output, failing…
test-driven-development
TDD: enforce RED-GREEN-REFACTOR, tests before code.
test-roadmap
EXPERIMENTAL. Analyzes a repository and any existing test suite, grades existing tests for weakness, classifies mocks, emits a phased roadmap for building a test suite that catches real regressions, then executes those phases one at a time. Use when planning or building a test suite, assessing whether existing tests…