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.
npx agentmods add commands/anilcancakir/claude-code/installgit clone --depth 1 https://github.com/anilcancakir/claude-codeWhat 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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00293 | $0.06991 |
| Opus 5 | $0.00147 | $0.03495 |
| Sonnet 5 | $0.00059 | $0.01398 |
| Haiku 4.5 | $0.00029 | $0.00699 |
Grade D, and why
install scanned grade D 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 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
Interactive setup for a machine that already has the ac plugin installed. This command tunes your user-scope environment: it generates your personal `my-coding` and `my-language` skills, merges the workflow-discipline se Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
- Workflow discipline (operating mode, code-lookup ladder, investigation, verification, delegation, web tools) lives in the global CLAUDE.md section this command merges, not in a skill. CLAUDE.md reaches every main-threa How it starts
The opening of the file, as written. The whole thing — 380 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/ac:install
Interactive setup for a machine that already has the ac plugin installed. This command tunes your user-scope environment: it generates your personal my-coding and my-language skills, merges the workflow-discipline section into your global ~/.claude/CLAUDE.md, and configures ~/.claude/settings.json so the ac workflow replaces the matching Claude Code built-ins. Safe defaults apply silently; security-sensitive keys and your MCP token are opt-in and never rendered in plaintext.
Request: $ARGUMENTS
Precondition: the ac plugin is already installed and loaded (you are running this as /ac:install). This command does not bootstrap the install. It never calls /plugin marketplace add or /plugin install. It writes only under ~/.claude/ and only the files each phase names.
Phase 0: Identity, Arguments, and Preflight
You are the /ac:install orchestrator. You interview the user, delegate skill creation to ac:skill-creator, and write user-scope config files behind explicit gates.
CAN: Use Read, Write, Edit, Bash, AskUserQuestion. Invoke ac:skill-creator via the Skill tool (Phases 1 and 2). Probe the ac MCP server by calling mcp__plugin_ac_ac__resolve-library. Write a ~/.claude/CLAUDE.md.proposed sidecar and a ~/.claude/settings.json.bak-ac-install backup.
CANNOT: Hand-write my-coding or my-language SKILL.md content; that is ac:skill-creator's job. Blind-overwrite ~/.claude/CLAUDE.md or ~/.claude/settings.json; both go through merge plus a gate or a backup. Run /plugin marketplace add or /plugin install. Edit files outside ~/.claude/. Write an allow rule broader than the literal server segment (mcp__plugin_ac_ac__*, never mcp__*).
MUST: Honor every flag from 0a for the rest of the run. Under --dry-run, render every planned change but call no Write or Edit. Back up ~/.claude/settings.json before the Phase 4 merge. Skip a skill that already exists unless the user chooses Recreate. Keep the merged global CLAUDE.md within the 200-line guidance; the Phase 3 fenced block is roughly 85 lines, so trim the operator's own content rather than the discipline sections if the total would overflow.
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.
- 2d ago First seen · 380 lines · 0 tokens per session scan D ca7601b27999
install is a command published in the GitHub repository anilcancakir/claude-code (3 stars, last pushed 13d ago), licensed MIT. It adds 293 tokens to every session and 6,991 once invoked, about $0.0015 per session on Opus 5. A static security scan graded it D with 2 findings (reads agent configuration directories, recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
constitution
Create or update the project constitution from interactive or provided principle inputs.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.