improve-skill

improve-skill is a command for coding agents from JavanC/Homunculus. It costs 0 tokens per session (462 once invoked), scanned A, original, MIT.

A command that repeatedly evaluates and improves a skill until its evaluation results stop improving or a limit is reached. An evaluation is a set of tests that checks how well the skill performs.

In plain words
What is it for?
Use it to test a skill, analyze failed or partial scenarios, update its instructions, increase its version, compare scores, and roll back when results regress.
Why use it?
It replaces manual guesswork with a measured improvement cycle and detects regressions when a change makes an earlier result worse.

Command

Install

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.

agentmods
npx agentmods add commands/javanc/homunculus/improve-skill
Clone the repo
git clone --depth 1 https://github.com/JavanC/Homunculus

Wrote 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.

agentmods badge for improve-skill

README.md
[![agentmods](https://agentmods.dev/badge/commands/javanc/homunculus/improve-skill.svg)](https://agentmods.dev/commands/javanc/homunculus/improve-skill)
Your own site
<a href="https://agentmods.dev/commands/javanc/homunculus/improve-skill"><img src="https://agentmods.dev/badge/commands/javanc/homunculus/improve-skill.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 462 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.00462
Opus 5 $0.00000 $0.00231
Sonnet 5 $0.00000 $0.00092
Haiku 4.5 $0.00000 $0.00046

Measured 4d ago against content hash 5a71679bc355, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 4d 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.

commands/improve-skill.md · 55 lines

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

  1. Verify target skill and eval spec exist
  2. Run initial eval, record baseline score
  3. 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)
  4. 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
Changes

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.

  1. 4d ago First seen · 55 lines · 0 tokens per session scan A 5a71679bc355

Subscribe to this mod's changes

improve-skill is a command published in the GitHub repository JavanC/Homunculus (15 stars, last pushed 3mo ago), 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.