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/juan294/cc-rpi/bootstrapgit clone --depth 1 https://github.com/juan294/cc-rpiWhat 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 | $0.00000 | $0.01451 |
| Opus 5 | $0.00000 | $0.00726 |
| Sonnet 5 | $0.00000 | $0.00290 |
| Haiku 4.5 | $0.00000 | $0.00145 |
Grade A, and why
bootstrap 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 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.
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 — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bootstrap New Project from cc-rpi Blueprint
Model tier: sonnet — Sonnet 5 (1M context) session.
You are setting up a new project using the cc-rpi blueprint repository. The blueprint lives at <path-to-your-cc-rpi-clone>/.
Phase 1: Learn the Rules
Read these files from cc-rpi IN ORDER. Do not skip any.
patterns/quick-reference.md— The INDEX of operational rules, one line each, naming the skill, rule file, or command that holds the rule body. Read it to learn what rules exist and where they live; you do not need to memorize them, because each body loads at its point of use once the skills and rules are installed.methodology/README.md— Read the one-paragraph summary and the reading order. You do NOT need to read every methodology file right now — you'll reference them as needed during actual work.
The error-patterns skill provides condensed error reference on demand
during debugging. The full 64-error catalog
(patterns/agent-errors.md) is available but not required for
onboarding.
Phase 2: Understand the Templates
Read these files to understand what you'll be creating:
templates/setup-checklist.md— This is your step-by-step guide. You'll execute it in Phase 3.templates/CLAUDE.md.template— The starting point for this project's CLAUDE.md.templates/AGENTS.md.template— The Codex compatibility layer for this project's AGENTS.md.templates/settings.json.template— The starting point for .claude/settings.json.
Phase 3: Set Up This Project
Now execute the setup checklist against THIS project. Work through it section by section:
- Ask me what type of project this is (web app, library, CLI, monorepo, Python, static site) so you can adapt accordingly.
- Ask me for the project name, description, stack, and any specifics you need to fill in the templates.
- Create the CLAUDE.md — adapt from the template, manually crafting every line for this project's needs.
- Create the AGENTS.md — adapt from the template so Codex can follow this project's cc-rpi setup too.
- Create
.claude/settings.json— adapt from the template. - Create
.claude/commands/— copy slash commands fromcc-rpi/templates/commands/and adjust file paths. - Install skills from
cc-rpi/templates/skills/to.claude/skills/:- Always install:
shell-tools/,git-workflow/,multi-agent/,deployment-safety/,ci-workflow/,github-cli/,error-patterns/,systematic-debugging/ - If Python project: also install
python-rules/ - If macOS development: also install
macos-rules/ - If using Supabase: also install
supabase/ - Each skill is a directory with a SKILL.md file -- copy the entire directory.
- Always install:
- Install rules from
cc-rpi/templates/rules/to.claude/rules/:- Always copy:
rpi-details.md,push-accountability.md - If deployment pipeline exists: copy
deployment-safety.md - If using Supabase: copy
supabase.md - If test framework detected: copy
testing.md - Adapt
pathsin frontmatter to match the project's actual file structure.
- Always copy:
- Create the directory structure (
docs/research/,docs/plans/,docs/decisions/). - Install release verification (E2E Pro) — copy
cc-rpi/templates/e2e-pro-playbook-template.mdinto the project (e.g.docs/release/e2e-pro-playbook.md) and complete its Project Adaptation Profile with verified values. Adopt Wave A always (the truthful release gate); adopt Waves C–H by project risk. See the setup checklist's "Release Verification (E2E Pro)" section. - Set up the README with the standard header.
- Add
.claude/settings.local.jsonto.gitignore. If scheduled agents will be used, also check repo visibility withgh repo view --json visibility --jq '.visibility': onPUBLIC(or no remote), adddocs/agents/,logs/, andscripts/agents/to.gitignore(Rule #70); onPRIVATE/INTERNAL, leave them tracked. - Walk through the remaining checklist items (pre-commit hooks, CI, git setup) — ask me for decisions where needed.
- Unless the user explicitly opts out, always make the project Codex compatible by creating
AGENTS.md. - If the user says "make this Codex compatible", treat that as an explicit instruction to create or update
AGENTS.mdand verify the Codex compatibility layer is complete.
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 · 93 lines · 0 tokens per session scan A b257e7075fe0
bootstrap is a command published in the GitHub repository juan294/cc-rpi (5 stars, last pushed 13d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,451 tokens. 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 2026-08-31.
Other commands, from other repositories
five
Apply the Five Whys root cause analysis technique to investigate an issue.
safe-refactor
Safe refactoring with automated review, testing, and rollback capabilities.
test
Smart test runner with filtering, coverage, and health monitoring.
vd-arch-review
Audita arquitetura de código em 3 níveis (macro/meso/micro). Detecta separação de camadas, anti-patterns, vazamento de abstração, dependências externas vs código customizado, acoplamento. User-invoked, sob demanda, para devs (não leigo). Use quando o usuário pede "auditoria arquitetural", "code review arquitetural"…
vd-manual
Rodado automaticamente dentro do /vd-close (opt-out via flag --no-manual).
vibeshield-code-review
Review a code diff or PR against two axes: Standards (does the code follow VibeDev conventions?) and Spec (does it implement what the spec said?). Returns a list of findings with severity, axis, and suggested fix.