distill

A command that turns lessons from recent agent runs into a reusable instruction or package. It can also use a file containing an AI response as its source.

In plain words
What is it for?
Use it after a successful task to record a repeatable method, the signs that led to it, and how it was checked.
Why use it?
It helps preserve useful solutions so they can be reused instead of rediscovered. It also explains what lesson was extracted and what evidence supports it.

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/evomap/evolver-claude-code-plugin/distill
Clone the repo
git clone --depth 1 https://github.com/EvoMap/evolver-claude-code-plugin
Per session 21 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 225 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 $0.00021 $0.00225
Opus 5 $0.00010 $0.00112
Sonnet 5 $0.00004 $0.00045
Haiku 4.5 $0.00002 $0.00022

Measured 2d ago against content hash 17ba30acde67, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

distill 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 2d 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/distill.md · 17 lines

What it actually says

Distill Evolver run history into a reusable skill/gene.

If evolver_distill_conversation is available in the MCP tool list and the reusable lesson came from this conversation, prefer calling that tool first with a concrete summary, signals, strategy, artifacts, and validation evidence. It lets the local Proxy quality-gate, persist, and queue Hub publishing for the resulting Gene/Capsule.

EVOLVER="evolver"; command -v evolver >/dev/null 2>&1 || EVOLVER="npx -y @evomap/evolver"
$EVOLVER distill $ARGUMENTS

Explain to the user what was distilled (the candidate skill/gene and the signals it generalizes), and remind them that only assets produced through genuine Evolver self-evolution are eligible to be published to the EvoMap skill store via /evolver:sync.

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. 2d ago First seen · 17 lines · 21 tokens per session scan A 17ba30acde67

Subscribe to this mod's changes

distill is a command published in the GitHub repository EvoMap/evolver-claude-code-plugin (12 stars, last pushed 12d ago), licensed MIT. It adds 21 tokens to every session and 225 once invoked, about $0.0001 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.