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/friedbotstudio/baseline/init-projectgit clone --depth 1 https://github.com/friedbotstudio/baselineWhat 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 | $0.00108 | $0.04151 |
| Opus 5 | $0.00054 | $0.02076 |
| Sonnet 5 | $0.00022 | $0.00830 |
| Haiku 4.5 | $0.00011 | $0.00415 |
Grade A, and why
init-project 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 yesterday.
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.
How it starts
The opening of the file, as written. The whole thing — 216 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/init-project — bootstrap the baseline for THIS project
User-only command. The 9-step protocol below mirrors seed.md §13. Each step is shown to the user; nothing happens silently.
Skip steps already completed (e.g., re-runs after configured: true). Re-runs replace the §16 addendum wholesale; manual notes belong in a sibling section.
Log every step transition to .claude/state/init/<UTC-timestamp>.log so partial failures and re-runs are debuggable.
Step 1 — Welcome
- Print one line confirming you're at the repo root:
pwd, then list.mcp.json,CLAUDE.md,.claude/. - Read
.claude/project.json → configured. Tell the user one of:configured: false→ "First run. The baseline is in project-agnostic mode. I'll scout your codebase, ask the recommender what to tailor, and propose a config."configured: true→ "Re-running init. Will re-scout and replace §16 in seed.md. Continue? (otherwise abort.)"
- If
$ARGUMENTSwas provided, note it ("user hint:<...>") and feed it into Step 3 as a stack-detection prior.
Step 2 — Pre-flight deps
Verify the baseline's hard requirements + advisory ones:
| Required | Check command | If missing |
|---|---|---|
bash ≥ 4 |
bash --version |
Hard fail. The baseline cannot run. |
node + npx ≥ 18.17 |
which npx |
Hard fail. Hooks and skill helpers are Node ESM; MCP servers need npx. |
git repo |
git rev-parse --is-inside-work-tree |
Soft warn. Swarm worktree mode falls back to shared. |
plantuml CLI |
which plantuml |
Soft warn. plantuml_syntax_guard runs in guide mode and /spec-render refuses without it. |
For each soft warn, note it and proceed. For hard fails, stop here with the install command.
Step 3 — Codebase survey (whole-project, in main context)
Survey the WHOLE project — not a task slice. Do this directly with Read/Grep/Glob/Bash; do not delegate to a subagent (the only baseline subagent, swarm-worker, exists strictly for /swarm-dispatch parallelism). Capture structured findings:
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.
- yesterday First seen · 216 lines · 108 tokens per session scan A f7b54124f8b3
init-project is a command published in the GitHub repository friedbotstudio/baseline (11 stars, last pushed 5d ago), licensed Apache-2.0. It adds 108 tokens to every session and 4,151 once invoked, about $0.0005 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 2026-08-30.
Other commands, from other repositories
audit-agents-skills
Audit quality of agents, skills, and commands in a Claude Code project.
security-audit
Comprehensive security audit of your project AND Claude Code configuration. Analyzes secrets exposure, injection surfaces, dependencies, hook security, and produces a scored security posture assessment.
audit-quiz-coverage
Find quiz coverage gaps from recent guide/CHANGELOG/CC-releases changes and propose new questions.
worktree
Create a git worktree for isolated feature/fix work.
sync
Check guide/landing synchronization status.
init-docs
Fetch official Anthropic Claude Code docs and store as local baseline snapshot.