evolve

A pattern checker for recent Claude Code session records and project activity. It looks for repeated workflows and recommends skills, agents, or configuration changes based on those patterns.

In plain words
What is it for?
Use it to inspect recent sessions, filter patterns by time or domain, preview recommendations, or generate a recommended workflow improvement.
Why use it?
It can reveal recurring work that could be automated or organized better. By default it only suggests changes; generation must be requested explicitly.

Skill for Claude CodeCodex

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/billbuchanan-code/claude-code-power-setup/evolve
Any agent
npx skills add billbuchanan-code/claude-code-power-setup --skill evolve
Clone the repo
git clone --depth 1 https://github.com/billbuchanan-code/claude-code-power-setup

Made for: Claude Code, Codex.

Per session 72 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,454 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 2 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 $0.00072 $0.03454
Opus 5 $0.00036 $0.01727
Sonnet 5 $0.00014 $0.00691
Haiku 4.5 $0.00007 $0.00345

Measured yesterday against content hash 3dd66fe4a8a8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

evolve scanned grade C with 2 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

find ~/.claude/projects/ -name "*.jsonl" -mtime -${DAYS:-7} 2>/dev/null | head -20

Enumerates other installed skillsmediumAgent snooping

Other skills' SKILL.md files reveal prompts, capabilities and secrets that should be invisible to peers.

find ~/.claude/skills/ -name "SKILL.md" 2>/dev/null | head -20
skills/evolve/SKILL.md · 423 lines

How it starts

The opening of the file, as written. The whole thing — 423 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Instinct / Evolve: Session Pattern Analyzer

You are a lightweight pattern-detection agent. Your job is to analyze recent Claude Code session data, identify recurring behaviors and workflows, and recommend improvements -- new skills, agents, or configuration changes -- that would save the user time.

Input

$ARGUMENTS

Flags (parsed from $ARGUMENTS):

  • --days N: Look back N days (default: 7)
  • --min-occurrences N: Minimum repetitions to flag a pattern (default: 3)
  • --domain DOMAIN: Filter to a specific domain (e.g., "testing", "git", "database")
  • --generate: Actually create the recommended skill/agent file (default: preview only)
  • --dry-run: Explicitly preview without creating (same as default)

Data Sources

Scan the following locations for session data, in order of priority:

1. Session Transcripts (JSONL)

# Find JSONL session files
find ~/.claude/projects/ -name "*.jsonl" -mtime -${DAYS:-7} 2>/dev/null | head -20

# Also check for session logs in alternative locations
find ~/.claude/ -maxdepth 3 -name "*.jsonl" -mtime -${DAYS:-7} 2>/dev/null | head -20

For each JSONL file found, read and parse the entries. Each line is a JSON object representing a session event (prompt, tool call, response, error, etc.).

2. Git History (Supplementary)

# Recent commit patterns (what files change together)
git log --oneline --name-only --since="${DAYS:-7} days ago" 2>/dev/null | head -100

# Most frequently changed files
git log --name-only --since="${DAYS:-7} days ago" --pretty=format: 2>/dev/null | sort | uniq -c | sort -rn | head -20

3. Shell History (Supplementary)

# Recent Claude-related commands
grep -i "claude\|/skill\|/agent\|/plan" ~/.zsh_history 2>/dev/null | tail -50
grep -i "claude\|/skill\|/agent\|/plan" ~/.bash_history 2>/dev/null | tail -50

4. Existing Skills & Agents (Context)

# What skills already exist (to avoid duplicates)
find ~/.claude/skills/ -name "SKILL.md" 2>/dev/null | head -20
find .claude/skills/ -name "SKILL.md" 2>/dev/null | head -20

# What agents already exist
find ~/.claude/agents/ -name "*.md" 2>/dev/null | head -20
find .claude/agents/ -name "*.md" 2>/dev/null | head -20

Read the full file on GitHub · 423 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 · 423 lines · 72 tokens per session scan C 3dd66fe4a8a8

Subscribe to this mod's changes

evolve is a skill published in the GitHub repository billbuchanan-code/claude-code-power-setup (2 stars, last pushed 1mo ago), licensed MIT. It adds 72 tokens to every session and 3,454 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it C with 2 findings (reads agent configuration directories, enumerates other installed skills). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens