Borrowing it
Nothing to install: this file belongs to philipyaz/cos. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/philipyaz/cos/main/.claude/skills/mcp-bridge-setup/SKILL.mdgit clone --depth 1 https://github.com/philipyaz/cosWrote 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/philipyaz/cos/mcp-bridge-setup)<a href="https://agentmods.dev/skills/philipyaz/cos/mcp-bridge-setup"><img src="https://agentmods.dev/badge/skills/philipyaz/cos/mcp-bridge-setup.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 36 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Privilege Escalation · line 38 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- high Privilege Escalation · line 61 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- high Privilege Escalation · line 209 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- high Privilege Escalation · line 224 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- high Privilege Escalation · line 322 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- high Privilege Escalation · line 325 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- high Privilege Escalation · line 331 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- high Privilege Escalation · line 334 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- high Privilege Escalation · line 335 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- high Privilege Escalation · line 340 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- high Privilege Escalation · line 348 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- high Privilege Escalation · line 354 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- high Agent Snooping · line 245 Skill accesses MCP server configuration files (mcp.json). MCP configs contain server URLs, authentication tokens, and tool definitions — reading them allows the skill to discover and potentially abuse other tool integrations.Fix: Remove all code or instructions that read MCP configuration files (mcp.json). MCP server details should be managed by the agent runtime, not read by individual skills.
- high Tool Misuse · line 387 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- medium Rogue Agent · line 58 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- medium Rogue Agent · line 60 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- medium Rogue Agent · line 85 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- medium Rogue Agent · line 89 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- medium Rogue Agent · line 101 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- medium Rogue Agent · line 103 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00200 | $0.09518 |
| Opus 5 | $0.00100 | $0.04759 |
| Sonnet 5 | $0.00040 | $0.01904 |
| Haiku 4.5 | $0.00020 | $0.00952 |
Grade A, and why
mcp-bridge-setup scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s -X POST "$BOARD_BRIDGE_URL/mcp" \ How it starts
The opening of the file, as written. The whole thing — 507 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MCP bridge setup (stdio → Streamable HTTP for Cowork)
Why this exists
This skill wires the four core servers (board, calendar, guard, vault) — all stdio MCP
servers. (The optional openwhispr voice add-on and whatsapp each live in their own setup
skill — /openwhispr-mcp-setup, /whatsapp-mcp-setup — because each integrates an external app;
the four here are self-contained in this repo.) Two Claude clients consume them, and they register
differently — getting this wrong is the usual failure:
- Claude Cowork Desktop launches them directly as stdio
commandservers inclaude_desktop_config.json(validated 2026-06-01 — Cowork can spawn local stdio servers; the earlier "it can't, so bridge over HTTP" assumption was wrong). It does not accept HTTPurlentries in that file. → §5, the primary path for Cowork. - Claude Code connects over HTTP via
REPO/.mcp.json("type":"http"→localhost:8001–8005). Each HTTP endpoint is a supergateway bridge, kept alive by launchd — the "bridge" this skill is named for. (Claude Code could use stdio too, but a long-running bridge gives one supervised, always-on instance independent of which app is open.)
Claude Code ──HTTP──> localhost:8001/mcp ──supergateway(launchd)──> node board-server (stdio)
localhost:8003/mcp ──supergateway(launchd)──> node calendar-server (stdio)
localhost:8004/mcp ──supergateway(launchd)──> node guard-server (stdio) ──HTTP──> guard sidecar :8009
localhost:8005/mcp ──supergateway(launchd)──> node vault-server (stdio) ──Agent SDK──> Anthropic API
Cowork Desktop ──spawns stdio directly──────────────────────────────> node board / calendar / guard / vault (§5)
This repo's servers (mcp/):
| server | stdio command | env | bridge port |
|---|---|---|---|
| board | node mcp/board-server/server.mjs |
CRM_BASE_URL=$BOARD_URL |
8001 |
| calendar | node mcp/calendar-server/server.mjs |
CRM_BASE_URL=$BOARD_URL |
8003 |
| guard | node mcp/guard-server/server.mjs |
COS_GUARD_URL=$GUARD_SIDECAR_URL |
8004 |
| vault | node mcp/vault-server/server.mjs |
ANTHROPIC_API_KEY (from config/secrets.env via launch.sh) + COS_VAULT_DIR=$VAULT_DIR |
8005 |
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.
- 8d ago First seen · 507 lines · 200 tokens per session scan A 43fcb0e4406d
mcp-bridge-setup is a skill published in the GitHub repository philipyaz/cos (4 stars, last pushed today), licensed MIT. It adds 200 tokens to every session and 9,518 once invoked, about $0.0010 per session on Opus 5. A static security scan graded it A with 1 finding (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
opencode-plugin-idioms
Event hook payload shapes, session lifecycle timing, toast/TUI-route render boundaries, and child-session tagging conventions for OpenCode server (@opencode-ai/plugin) and TUI (@opencode-ai/plugin/tui) plugins, grounded in the vendored OpenCode source at references/opencode.
wiki-lint
Health-check a wiki vault. Finds orphan pages (no inbound links), dead wikilinks (point to non-existent pages), missing frontmatter fields, stale claims, empty sections, and pages absent from catalog.md. Produces a structured report with severity tiers and proposes concrete fixes — but does not auto-apply them unless…
self-align
Adversarial self-audit of the Kagan repo through four lenses — code quality & YAGNI, security, spec alignment, docs/AGENTS.md freshness — each finding self-assessed and reported by severity and confidence for the developer to action. Use only when explicitly asked to self-align, audit, or health-check the codebase; it…
meta-sync-template
Interactive flow to propagate the reference (.template) vault's plugins, snippets, and root docs to one or more configured vaults. Reads the active router config, lists every vault with online status, flags vaults missing obsidian-local-rest-api upfront, lets the user pick all or a subset, and optionally re-clones…
save
File the current Claude conversation (or a specific insight from it) as a structured wiki note. Auto-detects the right type (decision, answer, session-log, technique, ADR), writes appropriate frontmatter, places the file in the correct wiki folder, and updates catalog.md, journal.md, hot.md. Use when the user says…
wiki-boundary
Rank the "frontier" pages of a wiki — the crossroads many pages link to that stay thin inside — so you can decide where research would pay off most. Use when the user says "what should I write about next", "where are the gaps", "which pages need work", "find the thin hub pages", "boundary pages", "/wiki-boundary"…