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 skills add michalekz/claude-bridge --skill claude-bridge-setupgit clone --depth 1 https://github.com/michalekz/claude-bridgeWrote 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/skills/michalekz/claude-bridge/claude-bridge-setup)<a href="https://agentmods.dev/skills/michalekz/claude-bridge/claude-bridge-setup"><img src="https://agentmods.dev/badge/skills/michalekz/claude-bridge/claude-bridge-setup/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/michalekz/claude-bridge/claude-bridge-setup"><img src="https://agentmods.dev/badge/skills/michalekz/claude-bridge/claude-bridge-setup.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00000 | $0.01405 |
| Opus 5 | $0.00000 | $0.00702 |
| Sonnet 5 | $0.00000 | $0.00281 |
| Haiku 4.5 | $0.00000 | $0.00140 |
Grade B, and why
claude-bridge-setup scanned grade B with 2 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 10d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
cat ~/.claude/claude-bridge-statusline-wrapper.sh Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- Does `curl https://api.anthropic.com/api/oauth/usage` work from your machine? Corporate proxies may block it. How it starts
The opening of the file, as written. The whole thing — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
claude-bridge-setup — Live-data activation
The v0.9.0+ live-data architecture requires two additions to ~/.claude/settings.json:
- statusLine wrapper — writes CC per-render stdin JSON to
~/.claude-bridge/live/statusline.json. Optional passthrough to user's original statusLine. - PostToolUse hook — calls Anthropic OAuth
/api/oauth/usage(throttled ~1/min) as fallback rate-limits source. Writes to~/.claude-bridge/live/oauth-api.json.
Without at least one, peer_context_status and rate_limit_status return hasLiveData: false with a setupPointer.
Auto-setup path (recommended)
The plugin's bundled SessionStart hook (setup-check.cjs) does most of this for you:
- Detects the newest installed plugin version in cache dir
- Refreshes stable symlinks at
~/.claude/claude-bridge-{statusline,refresh-limits}.cjs - Auto-generates a wrapper script at
~/.claude/claude-bridge-statusline-wrapper.shthat preserves any pre-existing statusLine command as passthrough - Prints a banner on stderr with copy-paste snippets when setup is incomplete
If you saw a banner starting with ━━━ claude-bridge vX.Y.Z setup ━━━, follow its instructions. Otherwise apply the manual steps below.
Manual setup
Step 1 — statusLine wrapper
Edit ~/.claude/settings.json:
{
"statusLine": {
"type": "command",
"command": "~/.claude/claude-bridge-statusline-wrapper.sh"
}
}
The wrapper script is auto-generated by the plugin's SessionStart hook on first run. If it doesn't exist yet, restart Claude Code once, then verify with:
cat ~/.claude/claude-bridge-statusline-wrapper.sh
Step 2 — PostToolUse hook
Add to the same settings.json:
{
"hooks": {
"PostToolUse": [{
"matcher": ".*",
"hooks": [{
"type": "command",
"command": "node ~/.claude/claude-bridge-refresh-limits.cjs",
"timeout": 6
}]
}]
}
}
If PostToolUse already exists in your settings.json, merge into the existing array — don't replace.
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.
- 10d ago First seen · 109 lines · 0 tokens per session scan B e1f1d225f799
claude-bridge-setup is a skill published in the GitHub repository michalekz/claude-bridge (3 stars, last pushed 5d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,405 tokens. A static security scan graded it B with 2 findings (reads agent configuration directories, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
agent-ops
This skill should be used when the user asks about agent architecture, evaluation, metrics, production monitoring, debugging agents, or best practices for building reliable AI agents. Use for questions like "evaluate my agent", "set up production monitoring", "add guardrails", "detect hallucinations", "agent…
opik
This skill should be used when the user needs to add Opik tracing or integrations to their code, instrument an LLM application, or needs reference for Opik SDK usage (Python, TypeScript, REST API). Use for tasks like "add tracing", "instrument my code", "use trackopenai", "add OpikTracer", "what span types are…
watch
File sentinel that monitors the working directory for changes and marker comments, then auto-triggers appropriate skills. Poll-based via git diff against the last scan commit. Writes intake items for batch processing and routes marker actions through /do. Use for automatic reactions to file changes; do NOT use for…
live-preview
Mid-build visual verification loop. Takes screenshots of components during construction, not just after. Catches visual regressions and invisible features before they compound. Requires Playwright or similar screenshot tool.
marshal
Meta-orchestrator that takes any direction — broad, specific, or vague — and autonomously chains skills and context into actionable work. Gathers context from codebase, docs, and memory. Only asks the user when it genuinely cannot proceed. Single-session orchestrator.
wiki
Markdown-first knowledge base where the LLM acts as librarian. Ingests raw sources, compiles and interlinks topic files, self-maintains an index. No vector DB or embeddings required -- uses LLM-native navigation over structured markdown up to 400K words.