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/xiaolai/cc-suite/bridge-toolsgit clone --depth 1 https://github.com/xiaolai/cc-suiteWhat 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 | $0.00086 | $0.01191 |
| Opus 5 | $0.00043 | $0.00596 |
| Sonnet 5 | $0.00017 | $0.00238 |
| Haiku 4.5 | $0.00009 | $0.00119 |
Grade A, and why
bridge-tools 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.
How it starts
The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/cc-suite:bridge-tools
Mirror the project MCP surface — .mcp.json plus the pinned claude-octopus server (so each tool can delegate to, and read the session history of, Claude) — into the additional coding agents enabled in .cc-suite.md.
Registry-bridged tools and their native MCP targets:
| Tool | Target | China tier |
|---|---|---|
| Grok Build (xAI) | .grok/config.toml ([mcp_servers.*]) |
C — VPN-only in mainland China |
| opencode (SST) | opencode.json (mcp, type local/remote) |
A — works natively |
| Qwen Code (Alibaba) | .qwen/settings.json (mcpServers, httpUrl) + .qwen/skills symlink |
A — works natively |
| Kimi CLI (Moonshot) | ~/.kimi/mcp.json (mcpServers, global) |
A — works natively |
Grok Build, opencode, and Kimi CLI read AGENTS.md and the shared skills paths (.claude/skills / .agents/skills) natively, so instructions and skills need no mirroring for them.
Qwen Code does not, on either count — so the bridge compensates twice for it. Its skill scan covers only ~/.qwen/skills/ and .qwen/skills/, hence the symlink in the table above. Its default context file is QWEN.md (qwen-code 0.21.0 resolves ["QWEN.md"] whenever the setting is unset), so the bridge also writes context.fileName: ["AGENTS.md", "QWEN.md"] into .qwen/settings.json. Both are automatic; do not tell the user to hand-symlink QWEN.md.
If a user reports that qwen is ignoring AGENTS.md, check that .qwen/settings.json carries that context.fileName array — if it is missing, the project was bridged by an older cc-suite and needs a re-run of this command.
Claude Code, Codex CLI, and Antigravity keep their own bridges — this command never touches them.
Security: env-var values and remote headers are never written into a mirrored config (potential secrets; .grok/config.toml, opencode.json, and .qwen/settings.json are routinely committed to the repo). Servers that carry them are still mirrored (command/args/url), and the missing vars are reported so you can add them out of band.
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.
- 3d ago First seen · 97 lines · 86 tokens per session scan A 8ffb028bb4d9
bridge-tools is a command published in the GitHub repository xiaolai/cc-suite (44 stars, last pushed 24d ago), licensed ISC. It adds 86 tokens to every session and 1,191 once invoked, about $0.0004 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
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.