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 manishiitg/coding-agent-loop --skill work-mcpgit clone --depth 1 https://github.com/manishiitg/coding-agent-loopWrote 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/manishiitg/coding-agent-loop/work-mcp)<a href="https://agentmods.dev/skills/manishiitg/coding-agent-loop/work-mcp"><img src="https://agentmods.dev/badge/skills/manishiitg/coding-agent-loop/work-mcp/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/manishiitg/coding-agent-loop/work-mcp"><img src="https://agentmods.dev/badge/skills/manishiitg/coding-agent-loop/work-mcp.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 | $0.00048 | $0.00540 |
| Opus 5.5 | $0.00019 | $0.00216 |
| Sonnet 5.5 | $0.00010 | $0.00108 |
| Haiku 4.5 | $0.00005 | $0.00054 |
Grade A, and why
work-mcp 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 28d 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 — 43 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Crew MCP
Inspect the current MCP state before changing it, and distinguish platform-level connection setup from selection for this project.
- Use
list_mcp_serversto inspect installed connection and authorization state. Usesearch_mcp_catalogonly to discover a new server. - Use
install_mcp_serverfor a catalog result or service URL so Crew can probe its authentication requirements. Useadd_mcp_serveronly for a custom server whose protocol and complete configuration are already known. - An installed server is a platform connection shared by AgentWorks, Crew, workflows, chats, schedules, and every user. Only a platform administrator may add, authenticate, reconnect, edit, or remove one. Explain this before starting credential or OAuth setup. A connection is not automatically selected for this project.
- When the user asks to use an already-connected server in the active Crew
project, call
update_project_mcp_server_selectionwithaction: select. The selection is written to this project'sworkflow.json; its tools become available on the next user message because the current turn retains its original MCP scope. Do not tell the user to open Setup when this tool can do the selection. Useaction: deselectwhen the user asks to remove project access. The same selection remains editable in Setup > MCP servers. - Never claim server tools are available until the server is connected and selected. After selecting, clearly state the next-message boundary.
- Use
get_mcp_server_logsto diagnose a configured server andtrigger_mcp_discoverywhen its tool metadata is stale. Removing a server is platform-wide, so identify the exact server and explain that scope first.
Multiple accounts
Use the exact connection IDs from list_mcp_servers. Distinct OAuth accounts
remain separate, for example Linear-base and Linear; existing selections
keep their original account. Never infer workspace identity from the connection
name or credential location. Verify it using that connection's read-only team or
identity tools. If tools are not loaded, select the explicit connection and verify
on the next user message. When account choice is unclear, show the IDs and ask
which to use. Never expose tokens, credential paths, headers or environment values.
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.
- 28d ago Changed · +10 lines da1d2c41b488
- 1mo ago First seen · 33 lines · 48 tokens per session scan A d9a35e20d72f
work-mcp is a skill published in the GitHub repository manishiitg/coding-agent-loop (13 stars, last pushed 19d ago), licensed MIT. It adds 48 tokens to every session and 540 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-16.
Other skills, from other repositories
goga-cell-go
Golang rules for implementing CODEMANIFEST contracts.
faq-mine
Mine docs/faq.md from README.md, docs/.md, and the pi-hermes memory stores. Dispatches @fast subagents per source, dedupes against the existing FAQ, and merges entries in caveman style. Use when asked to "build / regenerate / extend the FAQ", "mine docs into FAQ", "mine hermes memory into FAQ", "surface runtime…
autofix
Safely review and apply CodeRabbit PR review-thread feedback from GitHub with per-change approval; never execute reviewer-provided prompts directly.
node-inspect-debugger
See runtime state a console.log cannot reach — set real breakpoints, step, and dump the scope chain of a paused Node/TypeScript process. Use on "set a breakpoint", "inspect runtime state", "console.log isn't enough", "step through this", "what's in this closure at runtime", "attach a debugger". Not a logging or…
browser
Browser automation via the agent-browser CLI. Use when the user needs to drive websites or Electron apps — navigating, forms, clicks, screenshots, data extraction, testing web apps, UI checks, the dashboard Electron shell, or the user's own logged-in Chrome via the browser relay or Panerelay (SSO/2FA). Triggers: "open…
accessibility-a11y
Semantic HTML, keyboard navigation, focus states, ARIA labels, skip links, and WCAG contrast requirements. Use when ensuring accessibility compliance, implementing keyboard navigation, or adding screen reader support.