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/outlmd/outl/markdowngit clone --depth 1 https://github.com/outlmd/outlWhat 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 | $0.00682 | $0.00682 |
| Opus 5 | $0.00341 | $0.00341 |
| Sonnet 5 | $0.00136 | $0.00136 |
| Haiku 4.5 | $0.00068 | $0.00068 |
Grade A, and why
outl markdown.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 today.
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 — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Markdown / documentation style
Flag when a *.md change introduces hard-wrapped prose (lines broken at ~70/80/100 chars mid-sentence).
Every prose *.md in this repo uses semantic line breaks: one sentence per line, breaking after ./!/? (and sometimes :), never at an arbitrary column.
What to flag:
- Prose paragraphs hard-wrapped at a column width.
- A sentence split across two or more lines for no reason.
- Tables rewritten to span multiple lines per row (must stay one row per line).
What to leave alone:
- Code fences, YAML frontmatter, ASCII tree diagrams — preserve exactly.
- Outline content (anything under
note-example/, real workspace pages, fixtures) — this is data in the outl dialect, not prose docs. - Single-line list items, headings, link references.
Scope: root CLAUDE.md, per-crate CLAUDE.md, docs/*.md, README.md, CHANGELOG.md, CONTRIBUTING.md, SECURITY.md, .github/*.md, .claude/agents/*.md, .claude/commands/*.md.
Root CLAUDE.md has the canonical rule under "Markdown / documentation style".
One owner per fact — link, don't duplicate
Every user-facing fact lives in exactly one docs/*.md. CLAUDE.md files link to it instead of copying the table or chord list.
When reviewing a PR, flag duplication of these surfaces between docs/*.md and any CLAUDE.md:
| Fact | Canonical home |
|---|---|
| Every keyboard shortcut (TUI + desktop + mobile) | docs/shortcuts.md |
outl CLI subcommands |
docs/cli.md |
| TUI manual (modes, overlays) | docs/tui.md |
| Outl markdown dialect + sidecar | docs/markdown-format.md |
| CRDT algorithm + invariants | docs/crdt.md |
| Storage trait + JSONL backend | docs/storage.md |
| Sync model | docs/sync.md |
| MCP wiring + recipes | docs/mcp.md + docs/mcp-recipes.md |
| Config file | docs/config.md |
| Theming palette | docs/theming.md |
| Dev loop | docs/development.md |
| Contributing policy | docs/contributing.md |
What a CLAUDE.md should carry: invariants, architectural decisions you don't get to revisit, crate-specific contracts, the reasoning behind a choice — things a contributor needs before touching code, not user reference.
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.
- today First seen · 53 lines · 682 tokens per session scan A d5cccb363f24
outl markdown.instructions.md is an instructions file published in the GitHub repository outlmd/outl (161 stars, last pushed yesterday), licensed MIT. It adds 682 tokens to every session, about $0.0034 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 2026-09-01.
Other instructions, from other repositories
reflect-open AGENTS.md
AGENTS.md instructions for team-reflect/reflect-open, covering purpose, what is reflect, product principles, agent workflow and development workflow.
mq commit.instructions.md
Instructions for harehare/mq: Use the following format for commit messages.
core copilot-instructions.md
Instructions for asdecided/core: These decisions are already accepted. Do not re-open or contradict them; ask the AsDecided MCP tools (getartifact, searchartifacts) for the full text before proposing a change that touches one.
telegramify-markdown AGENTS.md
Instructions for sudoskys/telegramify-markdown, covering telegramify-markdown agent guide, task routing, quick commands, project rules and architecture map.
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.
research-os AGENTS.md
Instructions for lxinfei5/research-os, covering researchos — constitution, §0 what this is, §1 directory discipline, §2 half-life (innovation 1) — memory design and §3 behavior pillars (innovations 2–5).