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/pankaj28843/docs-mcp-server/agents-mdgit clone --depth 1 https://github.com/pankaj28843/docs-mcp-serverWrote 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/instructions/pankaj28843/docs-mcp-server/agents-md)<a href="https://agentmods.dev/instructions/pankaj28843/docs-mcp-server/agents-md"><img src="https://agentmods.dev/badge/instructions/pankaj28843/docs-mcp-server/agents-md.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 | $0.00933 | $0.00933 |
| Opus 5 | $0.00466 | $0.00466 |
| Sonnet 5 | $0.00187 | $0.00187 |
| Haiku 4.5 | $0.00093 | $0.00093 |
Grade A, and why
docs-mcp-server 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 3d 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 — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
docs-mcp-server
This is the canonical repo instruction file for Codex, Claude Code, OpenCode,
GitHub Copilot, and other coding agents. CLAUDE.md is compatibility-only and
points here for Claude Code auto-discovery.
Multi-tenant MCP server for documentation search (FastMCP + BM25 + article-extractor).
Agent Compatibility
AGENTS.mdis canonical.CLAUDE.mdis compatibility-only for Claude Code..agents/skillsis canonical for repo-local skills..claude/skills,.codex/skills,.opencode/skills, and.github/skillsare compatibility symlinks to.agents/skills..github/copilot-instructions.mdpoints GitHub Copilot at these same repo instructions..claude/rules/contains detailed project rule documents referenced by this canonical file..claude/settings.jsonand.claude/settings.local.jsonremain Claude-specific permission/settings files.
Build & Test Commands
# Always prefix Python commands with uv run
uv sync --extra dev
uv run ruff format . && uv run ruff check --fix .
timeout 120 uv run pytest -m unit --cov=src/docs_mcp_server --cov-fail-under=95
timeout 120 uv run python integration_tests/ci_mcp_test.py
uv run mkdocs build --strict
Core Principles
- No backward compatibility - Break freely, delete legacy code
- Minimal code - Fewer lines over new layers, delete more than you add
- Deep modules, simple interfaces - Reduce complexity at boundaries
- Let exceptions bubble - No silent error handling
- >=95% test coverage - Enforced via pytest-cov
- Green-before-done - Never say "done" until tests pass
Architecture
AppBuilder(src/docs_mcp_server/app_builder.py) is the sole entry for wiring FastMCP routes, health endpoints, and startup logic.- Tenants are composed from
StorageContext,IndexRuntime, andSyncRuntime. - All schedulers implement
SyncSchedulerProtocol- HTTP endpoints never branch on tenant type. - Background tasks belong to owner objects with explicit
start/stop/drain. - Domain code never imports web framework, FastMCP, or HTTP layers; use DTOs at boundaries.
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.
- 3d ago First seen · 102 lines · 933 tokens per session scan A 3c3277497bbc
docs-mcp-server AGENTS.md is an instructions file published in the GitHub repository pankaj28843/docs-mcp-server (2 stars, last pushed 6d ago), licensed MIT. It adds 933 tokens to every session, about $0.0047 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 instructions, from other repositories
RivalSearchMCP AGENTS.md
Instructions for damionrashford/RivalSearchMCP, covering agents.md, project overview, development commands, setup & running and install dependencies.
RivalSearchMCP CLAUDE.md
Instructions for damionrashford/RivalSearchMCP, covering claude.md, project overview, development commands, setup & running and set up pre-commit hooks.
MCP-OpenStack-Ops copilot-instructions.md
Instructions for call518/MCP-OpenStack-Ops, covering github copilot instructions, 🚫 critical restrictions - always enforce, never execute these operations directly, python execution requirements and mcp tool safety control requirements.
mcp-plesk-dev-docs copilot-instructions.md
Instructions for barateza/mcp-plesk-dev-docs, covering plesk unified mcp server - ai agent instructions, project overview, architecture & components, core stack and data flow.
anydocs AGENTS.md
AGENTS.md instructions for kiyeonjeon21/anydocs, covering anydocs, a mounted server the agent never calls is worth nothing, the one number that matters, failure must be loud and and a dead end is the loudest failure of all.
terragrunt-mcp-server copilot-instructions.md
Copilot instructions for omattsson/terragrunt-mcp-server, covering terragrunt mcp server - ai assistant guide, architecture, key patterns, development and schema drift detection.