update

A command for refreshing the bridge between the cc-suite plugin and local MCP configuration after the plugin has been updated. It also checks that the pinned Claude Octopus package starts correctly.

In plain words
What is it for?
Run it after updating cc-suite to rewrite configuration, refresh the package cache, and verify the MCP connection.
Why use it?
It prevents local registrations and cached packages from becoming out of date after an update.

Command

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/xiaolai/cc-suite/update
Clone the repo
git clone --depth 1 https://github.com/xiaolai/cc-suite
Per session 42 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,164 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 $0.00042 $0.01164
Opus 5 $0.00021 $0.00582
Sonnet 5 $0.00008 $0.00233
Haiku 4.5 $0.00004 $0.00116

Measured 2d ago against content hash f66f23561c56, 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 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.

commands/update.md · 86 lines

How it starts

The opening of the file, as written. The whole thing — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CC-Suite Update

Use this after running claude plugin update cc-suite@xiaolai. The plugin-update command itself is a Claude Code operation — this command picks up where it leaves off: re-renders the cc-suite-managed bits of .codex/config.toml, ensures the new claude-octopus pin actually works on this machine, and reports any remaining staleness.

This is distinct from /cc-suite:repair. Repair is the recovery path when artifacts are broken or missing. Update is the deliberate refresh path after the plugin itself has moved.

Workflow

Step 1: Confirm the plugin has actually been updated

Read the currently-installed plugin version:

node -p "require('${CLAUDE_PLUGIN_ROOT}/.claude-plugin/plugin.json').version"

Tell the user the active version. If they haven't yet run claude plugin update cc-suite@xiaolai, stop and tell them to do that first. The update command cannot replace the running plugin; that's Claude Code's job.

Step 2: Re-render the bridge artifacts

Run every bridge script (mirrors what /cc-suite:repair would run). This is the user-side half of the coupled-release contract — every artifact the plugin owns gets rewritten against the current plugin's expectations.

bash    "${CLAUDE_PLUGIN_ROOT}/scripts/bridge_skills.sh"
bash    "${CLAUDE_PLUGIN_ROOT}/scripts/mcp_codex.sh"
bash    "${CLAUDE_PLUGIN_ROOT}/scripts/mcp_claude.sh"
bash    "${CLAUDE_PLUGIN_ROOT}/scripts/bridge_mcp.sh"
python3 "${CLAUDE_PLUGIN_ROOT}/scripts/bridge_hooks.py"
python3 "${CLAUDE_PLUGIN_ROOT}/scripts/bridge_agents.py"
python3 "${CLAUDE_PLUGIN_ROOT}/scripts/migrate_config.py"
python3 "${CLAUDE_PLUGIN_ROOT}/scripts/bridge_tools.py"

migrate_config.py tops up .cc-suite.md with any cc-suite-managed sections added since the project was initialized (e.g. ## Enabled Tools), preserving existing settings — this is how an existing project picks up new config surfaces after a plugin update. bridge_tools.py then mirrors the project MCP surface into any coding agents enabled in that section (no-op when none are enabled).

Read the full file on GitHub · 86 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. 2d ago First seen · 86 lines · 42 tokens per session scan A f66f23561c56

Subscribe to this mod's changes

update is a command published in the GitHub repository xiaolai/cc-suite (44 stars, last pushed 24d ago), licensed ISC. It adds 42 tokens to every session and 1,164 once invoked, about $0.0002 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.