Is the Agentsmd Optimize skill free?

Yes. The skill itself is free from majiayu000/spellbook. SkillProof publishes the install command and an independent test verdict at no cost.

What is the Agentsmd Optimize SkillProof Score?

9.2/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 8/10, docs & honesty 5/5.

How do I install Agentsmd Optimize?

Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.

Can I use Agentsmd Optimize with Cursor, Copilot, Gemini CLI, Codex or other AI tools?

The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.

Agentsmd Optimize

Audits a CLAUDE.md/AGENTS.md, verifies its claims against the repo, and applies approved fixes

by majiayu000 · majiayu000/spellbook

Tested · Works

Install — copy the command Download source ↗

Test report

Verdict: Tested · Works
Score: 9.2/10
Tested: Jul 31, 2026
Environment: Claude Code 2.x (agent harness)
Upstream re-checked: Aug 10, 2026 · db9bc06

Fetched the SKILL.md (self-contained prose, no scripts) and installed it into a temp HOME — it lands at ~/.claude/skills/agentsmd-optimize/SKILL.md, frontmatter parses with name+description, and a grep found no curl|sh/base64/exfiltration smells. For the output test I built a messy CLAUDE.md (wrong commands, a nonexistent application/ dir, a missing routing-contract.md ref) plus a real package.json; the baseline cleanup kept npm run start, yarn test, make build, the stale dir, and the broken ref verbatim, while following the skill's Step 2 verification (ls + package.json checks) caught that none exist and corrected them to npm run dev/npm test/npm run build, dropped the stale dir, and flagged the missing file instead of inventing it. Two artifacts (BASELINE_CLAUDE.md vs SKILL_CLAUDE.md) exist and the diff shows the concrete correctness difference.

Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works

Installs cleanly 5/5
Triggers reliably 5/5
Output vs. baseline 8/10
Docs & honesty 5/5

What Agentsmd Optimize does

Audits an existing CLAUDE.md or AGENTS.md instruction file against five structure patterns, verifies every path and command claim against the real repo (ls, package.json/Makefile), then applies the fixes the user approves in place. Triggers when the user asks to optimize, clean up, or fix their agent doc (English or Chinese phrasings like "优化 CLAUDE.md"), or when they say to apply fixes after an audit. Flags missing referenced files rather than inventing them and leaves auto-generated regions untouched.

How to install Agentsmd Optimize

git clone --depth 1 https://github.com/majiayu000/spellbook.git /tmp/agentsmd-optimize-src
mkdir -p ~/.claude/skills
cp -R /tmp/agentsmd-optimize-src/skills/agentsmd-optimize ~/.claude/skills/agentsmd-optimize
# Single self-contained SKILL.md, no external deps or scripts.
# Sibling skill referenced in the body: skills/agentsmd-audit (audit-only). Copy it too if you want both.
# Rule codes it cites (SEC-13, W-17, U-32) are the author's own global ruleset, not required to use the skill.

Skills live in ~/.claude/skills/ (global) or .claude/skills/ (per-project). Restart Claude Code after installing.

Commands — how to trigger Agentsmd Optimize

/agentsmd-optimize Audits a CLAUDE.md/AGENTS.md, verifies its claims against the repo, and applies approved fixes

It also activates on plain-language prompts like these:

Optimize my CLAUDE.md instruction file
Score my AGENTS.md against best practices
Apply the recommended fixes to my agent doc

Frequently asked questions

Is the Agentsmd Optimize skill free?: Yes. The skill itself is free from majiayu000/spellbook. SkillProof publishes the install command and an independent test verdict at no cost.
Does Agentsmd Optimize work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Jul 31, 2026. Verdict: Tested · Works. Fetched the SKILL.md (self-contained prose, no scripts) and installed it into a temp HOME — it lands at ~/.claude/skills/agentsmd-optimize/SKILL.md, frontmatter parses with name+description, and a grep found no curl|sh/base64/exfiltration smells. For the output test I built a messy CLAUDE.md (wrong commands, a nonexistent application/ dir, a missing routing-contract.md ref) plus a real package.json; the baseline cleanup kept npm run start, yarn test, make build, the stale dir, and the broken ref verbatim, while following the skill's Step 2 verification (ls + package.json checks) caught that none exist and corrected them to npm run dev/npm test/npm run build, dropped the stale dir, and flagged the missing file instead of inventing it. Two artifacts (BASELINE_CLAUDE.md vs SKILL_CLAUDE.md) exist and the diff shows the concrete correctness difference.
What is the Agentsmd Optimize SkillProof Score?: 9.2/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 8/10, docs & honesty 5/5.
How do I install Agentsmd Optimize?: Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
Can I use Agentsmd Optimize with Cursor, Copilot, Gemini CLI, Codex or other AI tools?: The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.