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 instructions/discourse/discourse-mcp/agents-mdgit clone --depth 1 https://github.com/discourse/discourse-mcpWhat 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 | $0.01809 | $0.01809 |
| Opus 5 | $0.00905 | $0.00905 |
| Sonnet 5 | $0.00362 | $0.00362 |
| Haiku 4.5 | $0.00181 | $0.00181 |
Grade A, and why
discourse-mcp AGENTS.md 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 2d 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 — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — Discourse MCP
MCP server exposing Discourse forum capabilities as tools/resources for AI agents.
Entry: src/index.ts → dist/index.js (binary: discourse-mcp). Node >= 24.
SDLC Commands
pnpm build # Compile TypeScript to dist/
pnpm typecheck # Type-check only (no emit)
pnpm lint # Run ESLint on src/
pnpm test # Run tests (requires build first)
pnpm clean # Remove dist/
Source Map
| Area | Files |
|---|---|
| Entry/CLI | src/index.ts |
| HTTP client | src/http/client.ts |
| Bounded directories | src/site/directories.ts |
| Tool registry | src/tools/registry.ts |
| Tool definitions/catalog | src/tools/definition.ts, src/tools/builtin/catalog.ts |
| Built-in toolsets | src/tools/toolsets.ts |
| Resource registry | src/resources/registry.ts |
| Built-in tools | src/tools/builtin/* |
| Tag-group lifecycle | src/tools/builtin/tag_groups/* |
| Workflow tools/adapters | src/tools/builtin/workflows/* |
| Remote tools | src/tools/remote/tool_exec_api.ts |
| Utilities | src/util/*.ts (logger, redact, json_response) |
Key Patterns
Tool Implementation
- Tools live in
src/tools/builtin/as typeddefineTool({...})definitions src/tools/builtin/catalog.tsis the ordered built-in collection;src/tools/registry.tsregisters it through the shared registrar- Every definition declares two independent registration dimensions:
availabilityis one mutually exclusive configuration gate:always,writes_enabled, orsite_selectiontoolsetsis a non-empty list of operator-facing domains; selected domains form a union while preserving catalog order
OPT_IN_TOOLSETSdomains are hidden when selection is omitted;--toolsets allexpands to every real domain. Definitions must not mix opt-in and default memberships.- Availability is not domain metadata, and toolsets do not replace write, authentication, or admin checks
- All tools return strict JSON (no Markdown) with
isError: trueon failure - Tools with
outputSchemamust validate normalized upstream data in the handler and usestructuredJsonResponse()sostructuredContentequals the JSON text fallback. Keep malformed/error results unstructured andisError: true. - Write tools use
writes_enabledand retain a call-time access check; they require--allow_writesand matchingauth_pairs
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.
- 2d ago First seen · 156 lines · 1,809 tokens per session scan A df7d394bc887
discourse-mcp AGENTS.md is an instructions file published in the GitHub repository discourse/discourse-mcp (74 stars, last pushed 8d ago), licensed MIT. It adds 1,809 tokens to every session, about $0.0090 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 instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.