.agents/skills/joycraft-optimize/SKILL.md
Audit your Claude Code or Codex session overhead — harness file sizes, plugins, MCP servers, hooks — and report actionable recommendations
npx skillsauth add maksutovic/joycraft joycraft-optimizeInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
You are auditing the user's AI development session for token overhead. Produce a conversational diagnostic report — no files created.
Check which platform is active:
.claude/ directory, CLAUDE.md.agents/ directory, AGENTS.mdIf both exist, run both checks. If neither, default to Claude Code checks and note the uncertainty.
.claude/skills/**/*.md. Count lines per file. Threshold: ≤200 lines each..agents/skills/**/*.md. Count lines per file. Threshold: ≤200 lines each.~/.claude/plugins/installed_plugins.json. List plugin names and versions. If not found, report "no plugins file found."~/.claude/settings.json, check enabledPlugins array. Show enabled vs installed count.~/.claude/settings.json, count entries under mcpServers. List server names.~/.codex/config.toml. List any plugin toggles. Note: Codex syncs its curated plugin marketplace at startup — this is a boot cost even if you don't use them.~/.codex/config.toml for MCP server entries. List server names.Read .claude/settings.json in the project directory. List all hook definitions under the hooks key — show the event name and command for each.
For Codex: note "hook auditing not yet supported on Codex."
Organize findings by category. Use pass/warn indicators:
## Session Overhead Report
### Harness Files
- CLAUDE.md/AGENTS.md: [N] lines [PASS ≤200 / WARN >200]
- Skills: [N] files, [list any over 200 lines]
### Plugins
- Installed: [N] ([list names])
- Enabled: [N] of [M] installed
- [If 0: "No plugins — zero boot cost from plugins."]
### MCP Servers
- Count: [N] ([list names])
- [If 0: "No MCP servers — zero boot cost from servers."]
### Hooks
- [N] hook definitions ([list event names])
### Recommendations
- [Specific, actionable items for anything over threshold]
- [e.g., "AGENTS.md is 312 lines — consider splitting reference sections into docs/"]
- [e.g., "3 MCP servers load at boot — disable unused ones in config"]
End with:
For deeper token optimization, see:
- Nate B Jones's token optimization techniques
- OB1 repo — Heavy File Ingestion skill and stupid button prompt kit
- Joycraft's token discipline guide
| Scenario | Behavior |
|----------|----------|
| Config files don't exist | Report "not found" for that check, don't error |
| No plugins installed | Report 0 plugins — this is good, say so |
| CLAUDE.md/AGENTS.md exactly 200 lines | PASS — threshold is ≤200 |
| ~/.claude/ or ~/.codex/ not accessible | Skip user-level checks, note limitation |
| Both platforms detected | Run both audits, report separately |
development
Spawn an independent verifier subagent to check an implementation against its spec -- read-only, no code edits, structured pass/fail verdict
development
Assess and upgrade your project's AI development harness — score 7 dimensions, apply fixes, show path to Level 5
testing
Wrap up a session — capture discoveries, verify, prepare for PR or next session
development
Produce objective codebase research by isolating question generation from fact-gathering — subagent sees only questions, never the brief