agentmods.dev

update

update is a command for coding agents from juan294/cc-rpi. It costs 0 tokens per session (2,350 once invoked), scanned A, original, MIT.

A command for synchronizing a project with the latest version of a cc-rpi blueprint, a reusable project setup and workflow template. It checks whether the project was previously adopted and updates its related files.

In plain words
What is it for?
Use it to update an existing cc-rpi project, review blueprint changes, and apply the needed synchronization steps.
Why use it?
It keeps an adopted project aligned with blueprint changes while stopping when the required cc-rpi setup is missing.

Command

Part of the cc-rpi plugin — 13 skills, 18 commands, 2 hooks shipped together

not rated 5 14d ago A scan 0 tokens original MIT
View the source file juan294/cc-rpi
Install

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.

agentmods
npx agentmods add commands/juan294/cc-rpi/update
Clone the repo
git clone --depth 1 https://github.com/juan294/cc-rpi

Or install cc-rpi, the plugin that ships this one along with the rest of its 13 skills, 18 commands, 2 hooks.

Wrote 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.

agentmods badge for update

README.md
[![agentmods](https://agentmods.dev/badge/commands/juan294/cc-rpi/update.svg)](https://agentmods.dev/commands/juan294/cc-rpi/update)
Your own site
<a href="https://agentmods.dev/commands/juan294/cc-rpi/update"><img src="https://agentmods.dev/badge/commands/juan294/cc-rpi/update.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,350 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.02350
Opus 5 $0.00000 $0.01175
Sonnet 5 $0.00000 $0.00470
Haiku 4.5 $0.00000 $0.00235

Measured 3d ago against content hash 4ce21904fa8c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

update 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 3d 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.

templates/commands/update.md · 159 lines

How it starts

The opening of the file, as written. The whole thing — 159 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Update Project from cc-rpi Blueprint

Model tier: sonnet — Sonnet 5 (1M context) session.

You are syncing this project with the latest cc-rpi blueprint. The blueprint lives at <path-to-your-cc-rpi-clone>/.

This command works for both interactive use (/update) and headless scheduled agents.

Prerequisites

Before starting, verify this project was bootstrapped or adopted from cc-rpi:

  • If .claude/commands/ exists with RPI commands (research, plan, implement, validate) → proceed.
  • If CLAUDE.md exists with "RPI Workflow" section → proceed.
  • If neither exists → this project hasn't been set up with cc-rpi. Tell the user to run /adopt first and stop.

Phase 1: Check for Updates

  1. Pull the latest cc-rpi: git -C <cc-rpi-path> pull --rebase

  2. Check if .claude/cc-rpi-sync.json exists in THIS project.

    • If YES: read it and note the lastSyncCommit hash.
    • If NO: this is the first sync. Treat everything as new.

  3. If lastSyncCommit exists:

    • Run git -C <cc-rpi-path> log --oneline <lastSyncCommit>..HEAD to see what changed.
    • Run git -C <cc-rpi-path> diff --name-only <lastSyncCommit>..HEAD to get changed files.
    • If nothing changed, report "Already up to date" and stop.

Phase 2: Internalize New Knowledge

Read these files from cc-rpi to internalize the latest rules and patterns:

  1. patterns/quick-reference.md — The INDEX of operational rules; each line names the surface holding that rule's body. Rule numbers are permanent, so a gap means a retired number, not a missing rule.
  2. methodology/README.md — Methodology overview.

The error-patterns skill provides condensed error reference on demand. On incremental syncs, read the full catalog (patterns/agent-errors.md) only when the diff changes error-pattern content and the added detail is needed.

On incremental syncs (lastSyncCommit exists), prioritize reading files that appear in the git diff. You can skip unchanged methodology files.

Phase 3: Update Slash Commands

Read the full file on GitHub · 159 lines

Changes

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.

  1. 3d ago First seen · 159 lines · 0 tokens per session scan A 4ce21904fa8c

Subscribe to this mod's changes

update is a command published in the GitHub repository juan294/cc-rpi (5 stars, last pushed 14d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,350 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.

LLMProject managementai-agentsbest-practicesclaude-codedeveloper-toolserror-patterns
Related

Other commands, from other repositories

safe-refactor

Safe refactoring with automated review, testing, and rollback capabilities.

PaulDuvall/ai-development-patterns · 12 tokens

test

Smart test runner with filtering, coverage, and health monitoring.

PaulDuvall/ai-development-patterns · 11 tokens

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"…

4pixeltechBR/VibeDev · 105 tokens

validate

Run SDLC compliance check against the current project. Validates build system, code quality, testing, CI/CD, security, documentation, VCS, and release configurations.

zircote-plugins/sdlc-quality · 36 tokens

setup-pm

Command "setup-pm" from xiaobei930/cc-best, covering /setup-pm - 包管理器配置, 快速使用, 检测当前配置, 设置项目首选为 pnpm and 设置全局首选为 bun.

xiaobei930/cc-best · 16 tokens

infer

Command "infer" from xiaobei930/cc-best, covering /infer - 模型推理, 适用场景, 通用推理流程, 1. 环境检查 and gpu 检查.

xiaobei930/cc-best · 5 tokens