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 skills/trycourier/courier-mcp/tool-docsnpx skills add trycourier/courier-mcp --skill tool-docsgit clone --depth 1 https://github.com/trycourier/courier-mcpWrote 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/trycourier/courier-mcp/tool-docs)<a href="https://agentmods.dev/skills/trycourier/courier-mcp/tool-docs"><img src="https://agentmods.dev/badge/skills/trycourier/courier-mcp/tool-docs.svg" alt="Measured on agentmods" 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 | $0.00083 | $0.01039 |
| Opus 5 | $0.00042 | $0.00519 |
| Sonnet 5 | $0.00017 | $0.00208 |
| Haiku 4.5 | $0.00008 | $0.00104 |
Grade A, and why
tool-docs 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 4d 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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Keep tool docs in sync
The MCP server's public surface is the set of tools it registers. The canonical source of truth is the static readonly tools: string[] array in each mcp/src/tools/*.ts class, aggregated by CourierMcpToolsRegistry (mcp/src/utils/courier-mcp-tools-registry.ts):
defaultTools— every tool except the diagnosticConfigTools(get_environment_config). This is what the hosted server exposes.allAvailableTools—defaultToolsplus the diagnostic tools (available in local installs only).
When that set changes, several docs duplicate it and drift. Update all of them in the same PR.
Get the current tool list & counts
The tool set comes straight from the static readonly tools arrays. This reads them without a build (robust even if tsc is failing on unrelated errors):
node -e "
const fs=require('fs'), d='mcp/src/tools', names=new Set();
for (const f of fs.readdirSync(d)) {
if (!f.endsWith('.ts')) continue;
const m=fs.readFileSync(d+'/'+f,'utf8').match(/readonly tools\s*:\s*string\[\]\s*=\s*\[([\s\S]*?)\]/);
if (m) for (const x of m[1].matchAll(/'([a-z][a-z0-9_]+)'/g)) names.add(x[1]);
}
const a=[...names].sort(); console.log(a.join('\n')); console.log('TOTAL:', a.length);
"
The split between default and diagnostic (local-only) is defined by CourierMcpToolsRegistry: defaultTools is every tool except ConfigTools (get_environment_config); allAvailableTools adds it back. After a successful build you can read the exact counts straight from it:
node --input-type=module -e '
import { CourierMcpToolsRegistry as R } from "./mcp/dist/utils/courier-mcp-tools-registry.js";
console.log("total:", R.allAvailableTools.length, "| default:", R.defaultTools.length);
'
Docs to update
| File | What to update |
|---|---|
README.md |
The intro line ("… through N tools …"), the "D default tools … plus X diagnostic" line, and the per-category tables under Default tools and Diagnostic tools (local only) |
.plugin/plugin.json |
description — the "N tools for the full Courier API" count |
.cursor-plugin/plugin.json |
description — same count; keep it byte-identical to .plugin/plugin.json |
| Public docs site (separate repo) | trycourier/mintlify-docs → tools/mcp.mdx: the count sentence under Available Tools and the per-category tables (each tool links to its /api-reference/... page). If the repo is checked out as a sibling directory, update it and open a PR there; otherwise call out that a docs-site PR is still needed. |
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.
- 4d ago First seen · 65 lines · 83 tokens per session scan A 3fc3112ccc89
tool-docs is a skill published in the GitHub repository trycourier/courier-mcp (2 stars, last pushed 1mo ago), licensed MIT. It adds 83 tokens to every session and 1,039 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…