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/adoptgit clone --depth 1 https://github.com/juan294/cc-rpiWrote 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/juan294/cc-rpi/adopt)<a href="https://agentmods.dev/commands/juan294/cc-rpi/adopt"><img src="https://agentmods.dev/badge/commands/juan294/cc-rpi/adopt.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.02592 |
| Opus 5 | $0.00000 | $0.01296 |
| Sonnet 5 | $0.00000 | $0.00518 |
| Haiku 4.5 | $0.00000 | $0.00259 |
Grade A, and why
adopt 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 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.
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 — 186 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Adopt cc-rpi Best Practices into Existing Project
Model tier: sonnet — Sonnet 5 (1M context) session.
You are auditing and migrating an existing project to follow the cc-rpi blueprint. The blueprint lives at <path-to-your-cc-rpi-clone>/.
This project already exists and may already follow some, all, or none of these practices. Your job is to assess what's in place, identify gaps, and create a migration plan — NOT to blindly overwrite what's already working.
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 per rule naming the skill, rule file, or command that holds its body. Read it to learn what exists and where it lives, not to memorize rule text.methodology/README.md— Read the one-paragraph summary and reading order.
The error-patterns skill provides condensed error reference on demand.
The full catalog (patterns/agent-errors.md) is available when the
audit uncovers a debugging pattern that needs deeper detail, but it is
not required for onboarding.
3. templates/setup-checklist.md — Understand the target state for a fully set up project.
4. templates/CLAUDE.md.template — Know what a well-configured CLAUDE.md looks like.
5. templates/AGENTS.md.template — Know what the Codex compatibility layer should contain.
6. templates/settings.json.template — Know what settings.json should contain.
Phase 2: Audit This Project
Now investigate THIS project. Spawn parallel Explore agents to assess the current state:
Agent 1 — Configuration Audit:
- Does CLAUDE.md exist? If so, read it fully. How complete is it vs the template?
- Does AGENTS.md exist? If so, read it fully. Does it bridge Codex to the existing
.claude/*structure? - Does
.claude/settings.jsonexist? What permissions and env vars are configured? - Does
.claude/commands/exist? Which slash commands are present? - Does
.claude/skills/exist? Which skills are installed? - Does
.claude/rules/exist? Which rules are installed? (New in blueprint v2) - Does
.claude/agents/exist? - Is
.claude/settings.local.jsonin.gitignore? - Does CLAUDE.md contain
<important if>blocks? (These should migrate to.claude/rules/)
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 · +13 lines 7e9b8aca95e9
- 4d ago First seen · 173 lines · 0 tokens per session scan A 74f596eb7f37
adopt is a command published in the GitHub repository juan294/cc-rpi (5 stars, last pushed 3d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,592 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
awesome-chatgpt
Search awesome-ChatGPT-repositories for open-source GitHub repositories related to ChatGPT and LLMs.
test
Generate comprehensive tests.
commit
智能生成 Git 提交信息并提交.
pr
Handle the full workflow from current branch state to an open, CI-monitored pull request.
doctor.es
Diagnostica problemas de inferencia LLM en Mac: asiai doctor verifica el estado de los motores, conflictos de puertos, carga de modelos y estado de la GPU.
claude-request
Send a prompt to Claude Code via the LLM gateway with session tracking.