evolve

A command for grouping learned working patterns into reusable skills. An instinct here means a repeated behavior or rule observed from earlier sessions.

In plain words
What is it for?
Use it to analyze instincts, group them by topic or trigger, and draft a skill when enough consistent, confident examples exist.
Why use it?
It turns several related observations into one structured set of instructions when they form a clear pattern. This makes repeated practices easier for an agent to reuse.

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/fmflurry/settings-opencode/evolve
Clone the repo
git clone --depth 1 https://github.com/fmflurry/settings-opencode
Per session 4 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 566 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 $0.00004 $0.00566
Opus 5 $0.00002 $0.00283
Sonnet 5 $0.00001 $0.00113
Haiku 4.5 $0.00000 $0.00057

Measured yesterday against content hash 36c1e79a362f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

evolve 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 yesterday.

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/evolve.md · 113 lines

How it starts

The opening of the file, as written. The whole thing — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Evolve Command

Cluster related instincts into structured skills: $ARGUMENTS

Your Task

Analyze instincts and promote clusters to skills.

Evolution Process

Step 1: Analyze Instincts

Group instincts by:

  • Trigger similarity
  • Action patterns
  • Category tags
  • Confidence levels

Step 2: Identify Clusters

Cluster: Error Handling
├── Instinct: Catch specific errors (0.85)
├── Instinct: Wrap errors with context (0.82)
├── Instinct: Log errors with stack trace (0.78)
└── Instinct: Return meaningful error messages (0.80)

Step 3: Generate Skill

When cluster has:

  • 3+ instincts
  • Average confidence > 0.75
  • Cohesive theme

Generate SKILL.md:

# Error Handling Skill

## Overview
Patterns for robust error handling learned from session observations.

## Patterns

### 1. Catch Specific Errors
**Trigger**: When catching errors with generic catch
**Action**: Use specific error types

### 2. Wrap Errors with Context
**Trigger**: When re-throwing errors
**Action**: Add context with fmt.Errorf or Error.cause

### 3. Log with Stack Trace
**Trigger**: When logging errors
**Action**: Include stack trace for debugging

### 4. Meaningful Messages
**Trigger**: When returning errors to users
**Action**: Provide actionable error messages

Step 4: Archive Instincts

Move evolved instincts to archived/ with reference to skill.

Evolution Report

Evolution Summary
=================

Clusters Found: X

Cluster 1: Error Handling
- Instincts: 5
- Avg Confidence: 0.82
- Status: ✅ Promoted to skill

Cluster 2: Testing Patterns
- Instincts: 3
- Avg Confidence: 0.71
- Status: ⏳ Needs more confidence

Cluster 3: Git Workflow
- Instincts: 2
- Avg Confidence: 0.88
- Status: ⏳ Needs more instincts

Skills Created:
- skills/error-handling/SKILL.md

Instincts Archived: 5
Remaining Instincts: 12

Thresholds

Metric Threshold
Min instincts per cluster 3
Min average confidence 0.75
Min cluster cohesion 0.6

Read the full file on GitHub · 113 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. yesterday First seen · 113 lines · 4 tokens per session scan A 36c1e79a362f

Subscribe to this mod's changes

evolve is a command published in the GitHub repository fmflurry/settings-opencode (172 stars, last pushed 19d ago), licensed MIT. It adds 4 tokens to every session and 566 once invoked, about $0.0000 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.