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/improve-skill)<a href="https://agentmods.dev/commands/javanc/homunculus/improve-skill"><img src="https://agentmods.dev/badge/commands/javanc/homunculus/improve-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/improve-skill"><img src="https://agentmods.dev/badge/commands/javanc/homunculus/improve-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 | $0.00462 |
| Opus 5.5 | $0.00000 | $0.00185 |
| Sonnet 5.5 | $0.00000 | $0.00092 |
| Haiku 4.5 | $0.00000 | $0.00046 |
Grade A, and why
improve-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.
What it actually says
/improve-skill — Auto-Improve an Evolved Skill
Iteratively improve a skill until its eval passes, using an eval → improve loop.
Flow
┌─── Round 1 ──────────────────────────┐
│ 1. /eval-skill → baseline score │
│ 2. Analyze FAIL/PARTIAL/GAP │
│ 3. Modify skill file │
│ 4. Bump version +0.1 │
│ 5. Re-eval │
│ 6. Compare scores: │
│ ├─ Improved (≥5pp) → next round │
│ ├─ Noise (<5pp) → stop │
│ └─ Regressed (≤-5pp) → rollback │
└──────────────────────────────────────┘
↓ (max 5 rounds)
Steps
- Verify target skill and eval spec exist
- Run initial eval, record baseline score
- Improve loop (max 5 rounds):
a. Analyze failing scenarios
b. Modify skill file:
- FAIL → fix incorrect info or add missing rules
- PARTIAL → add detail
- GAP → add new section c. Increment version (1.1 → 1.2 → 1.3...) d. Re-eval e. Compare scores (apply noise tolerance: 5pp)
- Output improvement report
Regression Detection
If a previously passing scenario now fails:
- Mark as REGRESSION
- Must fix regression before continuing
- If unable to fix, rollback to previous version
Gaming Gate
If score jumps >5pp but net new lines ≤ 3 → gaming_suspected. Revert and add genuinely missing knowledge instead. See /eval-skill Gaming Gate section for details.
Notes
- Only modify the skill file, never the eval spec (tests stay fixed)
- All intermediate versions tracked via git
- Score delta < 5pp = statistical noise, not real improvement
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 · 55 lines · 0 tokens per session scan A 5a71679bc355
improve-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 462 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.