evolve

A skill for applying accumulated changes to a project’s Claude configuration. It checks recorded file, plugin, MCP, skill, and agent changes before deciding whether updates are needed.

In plain words
What is it for?
It is for updating onboarding and integration sections after tooling changes, draining queued drift records, and detecting differences between saved configuration and the current project setup.
Why use it?
It prevents Claude configuration from falling out of sync after project files or installed tools change.

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/apurvbazari/claude-plugins/evolve
Any agent
npx skills add ApurvBazari/claude-plugins --skill evolve
Clone the repo
git clone --depth 1 https://github.com/ApurvBazari/claude-plugins

Made for: Claude Code, Codex.

Per session 51 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 8,197 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 $0.00051 $0.08197
Opus 5 $0.00026 $0.04098
Sonnet 5 $0.00010 $0.01639
Haiku 4.5 $0.00005 $0.00820

Measured 2d ago against content hash 58650287841c, 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 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.

onboard/skills/evolve/SKILL.md · 355 lines

How it starts

The opening of the file, as written. The whole thing — 355 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Evolve Skill — Apply Pending Drift Updates

You are applying accumulated tooling drift updates. This skill handles two drift sources: FileChanged drift (logged by hooks to .claude/onboard-drift.json, or the legacy .claude/greenfield-drift.json in projects onboarded before the rename) and plugin drift (detected by comparing the baseline in onboard-meta.json against currently-installed plugins).

Guard

Check both drift sources before deciding whether to proceed:

  1. Read .claude/onboard-drift.json in the project root (falling back to the legacy .claude/greenfield-drift.json if only that exists — see § Legacy drift-file migration). Record whether it has entries.
  2. Read .claude/onboard-meta.json. If it contains detectedPlugins.installedPlugins, run the plugin drift detection from Step 0 below. Record whether plugin drift was found.

If onboard-drift.json has no entries (or is missing) AND no plugin drift was detected AND no MCP drift was detected (Step 2c pre-check against .claude/onboard-mcp-snapshot.json) AND no skill frontmatter drift was detected (Step 2d pre-check against .claude/onboard-skill-snapshot.json) AND no agent frontmatter drift was detected (Step 2e pre-check against .claude/onboard-agent-snapshot.json) AND no output-style drift was detected (Step 2f pre-check against .claude/onboard-output-style-snapshot.json) AND no LSP drift was detected (Step 2g pre-check against .claude/onboard-lsp-snapshot.json) AND no built-in skills drift was detected (Step 2h pre-check against .claude/onboard-builtin-skills-snapshot.json) AND no research staleness was detected (Step 2i pre-check against onboard-meta.json.research):

No pending drift detected. Your AI tooling is in sync with your codebase.

FileChanged drift is logged automatically when dependencies, configs, or structure change. Plugin drift is detected by comparing installed plugins against the baseline in onboard-meta.json. MCP / skill / agent / output-style / LSP / built-in skills drift is detected by comparing live files against their respective snapshots in .claude/. Research staleness is detected by re-checking the codebase against the stored research roster in onboard-meta.json.research.

Read the full file on GitHub · 355 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 355 lines · 51 tokens per session scan A 58650287841c

Subscribe to this mod's changes

evolve is a skill published in the GitHub repository ApurvBazari/claude-plugins (0 stars, last pushed 26d ago), licensed MIT. It adds 51 tokens to every session and 8,197 once invoked, about $0.0003 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 2026-08-31.