Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add anilcancakir/claude-code/plugin install acWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/anilcancakir/claude-code/init-project)<a href="https://agentmods.dev/commands/anilcancakir/claude-code/init-project"><img src="https://agentmods.dev/badge/commands/anilcancakir/claude-code/init-project/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/anilcancakir/claude-code/init-project"><img src="https://agentmods.dev/badge/commands/anilcancakir/claude-code/init-project.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00052 | $0.12928 |
| Opus 5.5 | $0.00021 | $0.05171 |
| Sonnet 5.5 | $0.00010 | $0.02586 |
| Haiku 4.5 | $0.00005 | $0.01293 |
Grade C, and why
init-project 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 today.
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.
**CAN**: Use `Read`, `Write`, `Edit`, `Grep`, `Glob`, `Bash`, `LSP`, `AskUserQuestion`. Spawn `Agent` with `subagent_type: "ac:explore"` for codebase fan-out, and one `ac:oracle` at Phase 3e to review the drafts. Invoke Reads MCP configurationmediumAgent snooping
mcp.json carries server URLs and auth tokens; reading it lets a mod discover and abuse other integrations.
prompt: "Discovery agent 4 of 4 for `/ac:init-project`. Target project: <PATH_ARG>. Predict the standard agent-infra footprint and report only deviations.\n\nCONTEXT: We are deciding whether the new CLAUDE.md should impo How it starts
The opening of the file, as written. The whole thing — 374 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/ac:init-project
Deep project investigation followed by an optimized CLAUDE.md, optional CLAUDE.local.md, up to five path-scoped .claude/rules/*.md files, permission rules that keep secrets unreadable and routine commands unprompted, a lint or format hook that provably fires, and a language server that provably answers. Everything is shown as one proposal and approved once before anything is written, and the drafts pass one ac:oracle review before they land. Drives the ac:claude-md-rules-creator skill as the writing playbook.
Request: $ARGUMENTS
Do NOT call EnterPlanMode or ExitPlanMode. This command runs on the main thread and uses no plan mode; the plugin's PreToolUse hook steers native plan mode to /ac:plan anyway.
Phase 0: Identity, Arguments, Primer, and Existing-File Branch
You are the /ac:init-project orchestrator. You investigate a target project, decide what standing instructions belong in which file shape, and leave the project with those files plus working tooling. You run on the main thread; the four discovery agents in Phase 1 and the Phase 3e reviewer are subagents you spawn.
CAN: Use Read, Write, Edit, Grep, Glob, Bash, LSP, AskUserQuestion. Spawn Agent with subagent_type: "ac:explore" for codebase fan-out, and one ac:oracle at Phase 3e to review the drafts. Invoke the ac:claude-md-rules-creator skill at Phase 3 entry (see the exact call in section 3a). Write <target>.proposed sidecar files when an existing target would be overwritten. Write one hook script under .claude/hooks/ and merge its entry, plus the approved permissions.deny and permissions.allow rules, into the target project's .claude/settings.json or .claude/settings.local.json as the 2d proposal named (Phase 4). Merge one enabledPlugins key into ~/.claude/settings.json after the 2d proposal is approved.
CANNOT: Spawn ac:librarian, or ac:oracle anywhere but 3e. ac:explore cannot spawn anything, because its tools: allowlist omits Agent; every discovery agent returns to this orchestrator before the next step. Author CLAUDE.md prose without first invoking ac:claude-md-rules-creator. Edit files outside the target project directory, with three exceptions: the enabledPlugins key of ~/.claude/settings.json in Phase 5, ~/.claude/<PROJECT_SLUG>-instructions.md in 3c for sibling worktrees, and the 3e scratch directory under ${TMPDIR:-/tmp}. Interview the user about MCP servers or about settings keys generally, or write any settings key other than one hooks.PostToolUse entry, permissions.deny and permissions.allow in the project and one enabledPlugins key in ~/.claude/settings.json. Write permissions.defaultMode in particular: auto and bypassPermissions are ignored in project and local settings since 2.1.257, and a mode is the user's choice, not the project's. Write anything to .claude/settings.json that the approved 2d proposal did not place there. Repair a pre-existing malformation in a settings file this command did not create.
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.
- today Changed · +6 lines 186521f0555d
- 22d ago Changed · +57 lines · -279 tokens per session scan B → C bbd2469cb2f2
- 1mo ago Changed · +74 lines · +56 tokens per session scan A → B 70c53410285f
- 1mo ago First seen · 237 lines · 275 tokens per session scan A fe943a468dca
init-project is a command published in the GitHub repository anilcancakir/claude-code (3 stars, last pushed today), licensed MIT. It adds 52 tokens to every session and 12,928 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it C with 2 findings (reads agent configuration directories, reads mcp configuration). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
recall-save
Generate / overwrite .recall/context.md with Recall's local offline summarizer.
notebook-query
Query the notebook knowledge base (SQLite) built by /agy:notebook — precise, grounded, cited. Ask in natural language ("sum the amounts by category", "which docs mention 'Acme Corp'", "build a project timeline") or pass raw SQL. Read-only. Use this when you need exact aggregates/lookups across a document corpus…
standup
Show a daily standup summary with completed, in-progress, and blocked tasks across all active epics.
ccc-orchestrate
Run a sequential multi-agent workflow (feature, bugfix, refactor, security or custom chain) with structured handoffs, plus optional tmux and worktree workers for long-running sessions. Use when a task needs planner, implementer and reviewer stages in order.
ralph-help
Explain Ralph Loop plugin and available commands.
design
A command that turns an existing plan into a detailed technical design for building the feature.