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/ojspace/md-anything/copilot-instructionsgit clone --depth 1 https://github.com/ojspace/md-anythingWhat 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 | $0.00903 | $0.00903 |
| Opus 5 | $0.00451 | $0.00451 |
| Sonnet 5 | $0.00181 | $0.00181 |
| Haiku 4.5 | $0.00090 | $0.00090 |
Grade A, and why
md-anything copilot-instructions.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 — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Copilot instructions for md-anything
Build, test, and lint commands
Use Bun throughout this repository.
bun install
bun run lint
bun run build
# Full suite
bun test
bun run test
# Contributor-safe required subset
bun run test:required
# Regenerate generated PDF/EPUB fixtures when needed
bun run test:fixtures
# Run a single test file
bun test tests/unit/detect-input.test.ts
# Run one test by name
bun test tests/integration/convert-text.test.ts -t "converts .txt file to markdown"
# Live/network tests
LIVE_TESTS=1 bun test tests/integration/youtube-live.test.ts tests/integration/url-live.test.ts
When debugging optional local tool support, run bun run src/cli.ts doctor.
High-level architecture
-
src/cli.tsandsrc/mcp.tsare the shipped entry points. They both build a runtime withcreateRuntimeProviders(DEFAULT_CONFIG)and delegate to shared core logic instead of implementing format-specific behavior themselves. -
The main conversion path lives in
src/core/convert.ts: validate withConvertRequestSchema, detect the input kind, route withrouteInput, normalize quality metadata withfinalizeDocument, attach chunk/provenance data, and render Markdown withformatMarkdown. -
src/providers/*contains one converter per input kind. Providers return aNormalizedDocument; they should not format final Markdown themselves. -
Runtime capability checks are centralized in
src/core/runtime.ts. Optional tools such astesseract,pdftotext,ebook-convert,unzip,ffmpeg,whisper-cpp, andwhisperare detected once and then passed through the runtime so providers can gate behavior consistently. -
src/core/ingest.tswalks supported files in a folder, converts them through the shared pipeline, and returns counts plus per-document metadata. It does not currently process source manifests or generate graph/index artifacts. -
src/mcp-support.tsis the MCP policy layer: it restricts local paths to the current workspace root, blocks private URLs by default, and defines structured tool output, resources, and prompts.
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 · 82 lines · 903 tokens per session scan A 77b3b751d45f
md-anything copilot-instructions.md is an instructions file published in the GitHub repository ojspace/md-anything (49 stars, last pushed 5mo ago), licensed MIT. It adds 903 tokens to every session, about $0.0045 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
book-to-skill CLAUDE.md
Claude Code instructions for virgiliojr94/book-to-skill, a project described as: Turn any technical book PDF into a Claude Code skill — ready to study, reference, and use while you work.
document-SKILLs AGENTS.md
Instructions for appautomaton/document-SKILLs, covering document skills, python, python packages, node.js and system tools (brew or apt-get).
easy-notion-mcp CLAUDE.md
Instructions for Grey-Iris/easy-notion-mcp, covering easy-notion-mcp, open source context, .meta/ publication policy (hybrid, 2026-07-02), standing priorities and commands.
mktero AGENTS.md
Instructions for tenglvjun/mktero, covering agents.md, project overview, commands, repository map and architecture and runtime rules.
go-docs-mcp CLAUDE.md
Instructions for drolosoft/go-docs-mcp, covering go-docs-mcp, build & run, architecture, key decisions and tools.
docsift CLAUDE.md
Instructions for anishmoncivarghese/docsift, covering docsift, key documents (read before making product decisions), commands, architecture (src layout, package docsift) and hard rules.