evolve-skill

evolve-skill is a command for Claude Code from iliaal/whetstone. It costs 32 tokens per session (1,996 once invoked), scanned A, original, MIT.

A command that runs a complete improvement process for one coding-agent skill, including collecting session data, building test examples, measuring results, and trying an automated rewrite.

In plain words
What is it for?
Use it to evolve a named skill with the GEPA, MIPRO, or bootstrap optimizer and review the before-and-after scores.
Why use it?
It helps compare the skill's current behavior with an optimized version using a repeatable evaluation process instead of relying only on personal judgment.

Command for Claude Code

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/iliaal/whetstone/evolve-skill
Clone the repo
git clone --depth 1 https://github.com/iliaal/whetstone

Made for: Claude Code.

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 evolve-skill

README.md
[![agentmods](https://agentmods.dev/badge/commands/iliaal/whetstone/evolve-skill.svg)](https://agentmods.dev/commands/iliaal/whetstone/evolve-skill)
Your own site
<a href="https://agentmods.dev/commands/iliaal/whetstone/evolve-skill"><img src="https://agentmods.dev/badge/commands/iliaal/whetstone/evolve-skill.svg" alt="Measured on agentmods" height="20"></a>
Per session 32 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,996 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 $0.00032 $0.01996
Opus 5 $0.00016 $0.00998
Sonnet 5 $0.00006 $0.00399
Haiku 4.5 $0.00003 $0.00200

Measured 3d ago against content hash 70f26c526290, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

evolve-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 3d 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.

.claude/commands/evolve-skill.md · 162 lines

How it starts

The opening of the file, as written. The whole thing — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Evolve a skill via DSPy optimization

Run the complete skill evolution pipeline for a single skill. Harvests fresh session data, discovers new negative patterns, builds a golden eval dataset, scores the baseline, runs DSPy optimization, and presents a before/after comparison for review.

Arguments

SKILL_NAME=$1  (required: e.g., "code-review", "pinescript", "planning")
OPTIMIZER=$2   (optional: "gepa" (default), "mipro", or "bootstrap")

Parse from: $ARGUMENTS

If no skill name provided, ask the user which skill to evolve. Show skills with the most harvested data as suggestions.

Pipeline

Maximize parallelism. Steps within the same group run concurrently (use background subagents or parallel bash). Steps across groups are sequential.

Group A (parallel): Harvest + Discover

Run these two concurrently:

Step 1: Harvest sessions (full, all projects)

python3 distillery/scripts/distiller.py harvest-sessions

Report: total examples harvested, how many attributed to the target skill.

Step 2: Discover new negative signal patterns

python3 distillery/scripts/distiller.py discover-signals --top 20

Present the top candidates to the user. If any look like genuine dissatisfaction patterns (not neutral task requests), ask whether to add them to _NEGATIVE_SIGNAL_PATTERNS in distiller.py before proceeding. If patterns are added, re-run harvest (Step 1) to update signal classifications.

If no new patterns worth adding, continue.

Group B (sequential): Build golden

Depends on Group A completing.

Step 3: Build golden eval dataset

RECOMMENDED (human-label) path — post-2026-07-07 harvest data is mostly ambiguous (no typed user outcome), and a golden set dominated by ambiguous drives GEPA to degenerate results:

python3 distillery/scripts/distiller.py build-golden <skill> --top 20
# → writes candidates.jsonl. Open it, set each "label" to positive / negative / skip
#   (drop the ambiguous ones as "skip" unless you can grade them), then:
python3 distillery/scripts/distiller.py approve-golden <skill>

Read the full file on GitHub · 162 lines

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. 3d ago First seen · 162 lines · 32 tokens per session scan A 70f26c526290

Subscribe to this mod's changes

evolve-skill is a command published in the GitHub repository iliaal/whetstone (32 stars, last pushed 4d ago), licensed MIT. It adds 32 tokens to every session and 1,996 once invoked, about $0.0002 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 2026-08-30.