evolve

evolve is a skill for Claude Code, Codex from epicsagas/epic-harness. It costs 45 tokens per session (1,253 once invoked), scanned A, original, Apache-2.0.

A command for reviewing past coding sessions and improving the skills used by the system.

In plain words
What is it for?
Use it to view session metrics and history, generate or improve skills, or roll back and reset evolution results.
Why use it?
It helps find recurring failures and weak areas instead of leaving the same problems unexamined.

Skill for Claude CodeCodex

Part of the epic plugin — 27 skills, 6 hooks shipped together

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 skills/epicsagas/epic-harness/evolve
Any agent
npx skills add epicsagas/epic-harness --skill evolve
Clone the repo
git clone --depth 1 https://github.com/epicsagas/epic-harness

Made for: Claude Code, Codex.

Or install epic, the plugin that ships this one along with the rest of its 27 skills, 6 hooks.

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

README.md
[![agentmods](https://agentmods.dev/badge/skills/epicsagas/epic-harness/evolve.svg)](https://agentmods.dev/skills/epicsagas/epic-harness/evolve)
Your own site
<a href="https://agentmods.dev/skills/epicsagas/epic-harness/evolve"><img src="https://agentmods.dev/badge/skills/epicsagas/epic-harness/evolve.svg" alt="Measured on agentmods" height="20"></a>
Per session 45 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,253 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 $0.00045 $0.01253
Opus 5 $0.00023 $0.00626
Sonnet 5 $0.00009 $0.00251
Haiku 4.5 $0.00005 $0.00125

Measured 4d ago against content hash 135f6e280cdc, 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 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.

skills/evolve/SKILL.md · 133 lines

How it starts

The opening of the file, as written. The whole thing — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/evolve — Manual Evolution Trigger

CRITICAL: Run HARNESS_DIR=$(epic path) first. NEVER use .harness/ in the project directory.

You are the Evolution Engine — analyze past sessions to improve skills.

Sub-commands

/evolve (default) — Run evolution now

  1. Read observation logs from $HARNESS_DIR/obs/
  2. Analyze failure patterns across all sessions
  3. Identify weak areas (error types, recurring failures)
  4. Generate or improve evolved skills in $HARNESS_DIR/evolved/
  5. Gate: validate new skills (format, dedup, cap of 10)
  6. Report what changed

/evolve status — Show evolution dashboard

Read $HARNESS_DIR/metrics.json and $HARNESS_DIR/evolution.jsonl, then display:

## Evolution Dashboard

### Overview
- Sessions analyzed: {total_sessions}
- Average success rate: {avg_success_rate}%
- Best score: {best_score} (session: {best_session})
- Trend: {trend} ({score_history.length} data points)
- Stagnation count: {stagnation_count} / 3 (rollback at 3)

### Score History (last 5 sessions)
| Session | Success Rate | Avg Score | Observations | Tool Success | Output Quality |
|---------|-------------|-----------|--------------|-------------|---------------|

### Evolved Skills
(list $HARNESS_DIR/evolved/*/SKILL.md with name and description from frontmatter)

### Last Session Analysis
(read last entry from evolution.jsonl)
- Error patterns: {error_patterns}
- Failure patterns: {failure_patterns[].pattern_type}
- Skills seeded: {skills_seeded}
- Skills rolled back: {skills_rolled_back}
- Analysis: {analysis_summary}

/evolve history — Long-term analysis

Read $HARNESS_DIR/evolution.jsonl (full history), then display:

## Evolution History

### Trend Over Time
| Session # | Date | Success Rate | Avg Score | Skills | Patterns |
|-----------|------|-------------|-----------|--------|----------|

### Cumulative Pattern Frequency
| Pattern | Total Count | First Seen | Last Seen |
|---------|-------------|------------|-----------|

### Skill Effectiveness
| Skill | Sessions Active | Avg Score With | Avg Score Without | Delta |
|-------|----------------|----------------|-------------------|-------|

### Dispatch Analysis
| Skill | Times Invoked | Top Trigger Signals |
|-------|--------------|---------------------|

Read the full file on GitHub · 133 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. 4d ago First seen · 133 lines · 45 tokens per session scan A 135f6e280cdc

Subscribe to this mod's changes

evolve is a skill published in the GitHub repository epicsagas/epic-harness (17 stars, last pushed today), licensed Apache-2.0. It adds 45 tokens to every session and 1,253 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.

Related

Other skills, from other repositories

mcporter

List, auth, and call MCP servers/tools from the terminal.

NousResearch/hermes-agent · 16 tokens

article-writing

Write articles, guides, blog posts, tutorials, newsletter issues, and other long-form content in a distinctive voice derived from supplied examples or brand guidance. Use when the user wants polished written content longer than a paragraph, especially when voice consistency, structure, and credibility matter.

affaan-m/ECC · 57 tokens

mem0-oss-to-platform

Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…

mem0ai/mem0 · 273 tokens

complete-partial-pr

Evaluate and complete an issue or PR where the submitted patch fixes only a narrow symptom of the reported pain point. Use when a contribution may miss adjacent integration surfaces, provider/spec semantics, roundtrip behavior, tests, docs, or historical maintainer decisions.

pydantic/pydantic-ai · 55 tokens

deploy-docker-compose

Run the Omnigent server as a Docker compose stack (server + Postgres) on any Docker host — your laptop, a VPS, EC2 by hand, or as the base layer of any container-platform deploy. Invoke when the user wants to build the image, bring up the compose stack, debug the stack on a host they already have, or extend the stack…

omnigent-ai/omnigent · 84 tokens

mapping-to-snomed

Maps clinical concept spans extracted by OpenMed to SNOMED CT concepts through a USER-SUPPLIED terminology server (the user's own Ontoserver, Snowstorm, or UMLS/UTS), never a bundled vocabulary. Use when the user wants to code findings, disorders, procedures, body structures, or substances to SNOMED CT, run an ECL…

maziyarpanahi/openmed · 205 tokens