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/claude-mdgit clone --depth 1 https://github.com/outlmd/outlWrote 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/outlmd/outl/claude-md)<a href="https://agentmods.dev/instructions/outlmd/outl/claude-md"><img src="https://agentmods.dev/badge/instructions/outlmd/outl/claude-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 | $0.08255 | $0.08255 |
| Opus 5 | $0.04127 | $0.04127 |
| Sonnet 5 | $0.01651 | $0.01651 |
| Haiku 4.5 | $0.00826 | $0.00826 |
Grade A, and why
outl CLAUDE.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 — 405 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — outl
Context for Claude Code sessions working on this repo. Read this before making any change.
What this project is
outl is a local-first outliner (Roam/Logseq replacement) with:
- Markdown as source of truth —
.mdfiles are 100% clean, no visible IDs. - Conflict-free sync via a tree CRDT (Kleppmann et al. 2022).
- Trait-based storage — JSONL (one file per actor) is the only persistent backend; ChronDB on the roadmap.
- TUI as a first-class citizen, not an afterthought.
- Journal-first — daily notes are the primary entry point.
Full spec lives in the README and docs/.
Don't skim — read.
Critical invariants (NEVER violate)
These are the non-negotiables. Violating any one breaks user trust irreversibly.
-
Op log is source of truth. All mutations go through
Op→apply_op→ log. The materialized tree and.mdfiles are projections. Never edit.mdto "fix" state. -
Markdown stays 100% clean. No
id::, no UUID inline, no HTML comments, nothing. IDs live ONLY in the.outlsidecar (JSON file next to the.md, e.g.pages/foo.outl). The sidecar is not a dotfile, because iCloud Documents (when used as the file transport) drops dotted paths during cross-device sync and silently breaks multi-device workspaces. Same rule applies toops/. -
CRDT follows Kleppmann 2022 literally.
do_op/undo_op/apply_op/creates_cyclemust match the paper. 100% coverage on these four is non-negotiable. -
Move that creates a cycle is a no-op on the materialized tree, but the op still goes into the log. Removing it breaks correctness of future reordering.
-
Storage is a trait, not a struct.
JsonlStorageis the only persistent impl, and tests useMemoryStorage. Anything that wants to persist ops goes throughdyn Storage. No second persistent backend lands without an issue + RFC first, because divergence between storages is exactly what we paid to remove in 0.5.0.
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 · 405 lines · 8,255 tokens per session scan A 4246f9bf7761
outl CLAUDE.md is an instructions file published in the GitHub repository outlmd/outl (165 stars, last pushed yesterday), licensed MIT. It adds 8,255 tokens to every session, about $0.0413 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
mq commit.instructions.md
Instructions for harehare/mq: Use the following format for commit messages.
core copilot-instructions.md
Copilot 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
Claude Code 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).
markview CLAUDE.md
Instructions for paulhkang94/markview, covering markview — ai development guide, quick reference, architecture, mcp tools (for ai integration) and safety rules.