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/JavanC/HomunculusWrote 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/commands/javanc/homunculus/eval-skill)<a href="https://agentmods.dev/commands/javanc/homunculus/eval-skill"><img src="https://agentmods.dev/badge/commands/javanc/homunculus/eval-skill/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/commands/javanc/homunculus/eval-skill"><img src="https://agentmods.dev/badge/commands/javanc/homunculus/eval-skill.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 | $0.00000 | $0.01246 |
| Opus 5.5 | $0.00000 | $0.00498 |
| Sonnet 5.5 | $0.00000 | $0.00249 |
| Haiku 4.5 | $0.00000 | $0.00125 |
Grade A, and why
eval-skill 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 2mo 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.
How it starts
The opening of the file, as written. The whole thing — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/eval-skill — Evaluate an Evolved Skill
Run scenario-based tests on a skill to measure its quality.
Steps
- List eval specs:
ls homunculus/evolved/evals/*.eval.yaml 2>/dev/null - If user specified a skill name, use that eval spec; otherwise let user choose
- Read the skill file (
homunculus/evolved/skills/<name>.md) and its eval spec
Evaluation
For each scenario, act as a developer who doesn't know the answer — only reference the skill document. Then compare against expected_behavior and anti_patterns.
Results
| Result | Condition |
|---|---|
| PASS | Skill guides all expected behaviors, no anti-patterns triggered |
| PARTIAL | Skill guides some expected behaviors, or misses important details |
| FAIL | Skill fails to guide correct behavior, or would cause anti-patterns |
| GAP | Scenario knowledge is completely absent from skill |
Report Format
🔬 Skill Eval: <name> v<version>
━━━━━━━━━━━━━━━━━━━━━━━━━━━━
Scenario Result Notes
──────────────────────────────────────
<scenario.name> PASS -
<scenario.name> PARTIAL Missing X
<scenario.name> FAIL Would cause Y
━━━━━━━━━━━━━━━━━━━━━━━━━━━━
Pass rate: X/Y (Z%)
Grade: ⭐⭐⭐⭐⭐ (>= 90)
Noise Tolerance
5pp rule: score delta < 5pp is statistical noise, not a real change. From Anthropic infrastructure noise research — environment variance alone can cause ±5pp swings.
|delta| < 5pp→not_significant(treat as flat)delta >= 5pp→ real improvementdelta <= -5pp→ real regression
Multiple-Run Modes
Three optional flags reduce measurement noise. Use independently or combined.
--runs N (eliminate infra noise)
/eval-skill my-skill --runs 3 — runs the full eval N times independently, reports mean ± σ.
- Eliminates session-to-session infrastructure variance
- Recommended for nightly agent evals:
--runs 3 - Daily manual evals: default N=1 is fine
📊 Multi-Run Summary (runs=3):
Run 1: 85% Run 2: 87% Run 3: 83%
Mean: 85.0% | σ: 1.6pp
Verdict: not_significant vs baseline 84% (delta=1pp < 5pp threshold)
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.
- 2mo ago First seen · 138 lines · 0 tokens per session scan A 59087a32857f
eval-skill is a command published in the GitHub repository JavanC/Homunculus (15 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,246 tokens. 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 2026-08-30.
Other commands, from other repositories
prototype
You are building a proof-of-concept for the current Grainulator sprint. Read CLAUDE.md for sprint context and claims.json for existing research claims.
qa-changes
This skill should be used when the user asks to "QA a pull request", "test PR changes", "verify a PR works", "functionally test changes", or when an automated workflow triggers QA validation of code changes. Provides a structured methodology for setting up the environment, exercising changed behavior, and reporting…
verify
Run repository verification using the verification-loop skill.
modernize-transform
Transform one legacy module to the target stack — idiomatic rewrite with behavior-equivalence tests.
constraints
A command for defining a project's quality standards through a short interview and a written CONSTRAINTS.md file. It records checks, thresholds, exceptions, and commands for enforcing them.
check-dev
Type-check a Z specification with fuzz.