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/rustgit 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 | $0.00995 | $0.00995 |
| Opus 5 | $0.00498 | $0.00498 |
| Sonnet 5 | $0.00199 | $0.00199 |
| Haiku 4.5 | $0.00100 | $0.00100 |
Grade A, and why
outl rust.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 — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Rust quality bar
Comment when the diff introduces any of the following. Skip when the existing surrounding code already does it (that's a separate cleanup).
.unwrap()outside#[cfg(test)]— require.expect("explicit reason")or?propagation. Theexpectmessage must name the invariant being asserted, not just "should not fail"..unwrap_or_default()masking an error path — if the default is a silent data-loss bug, flag it.unsafeinoutl-corewithout a// SAFETY:comment naming the invariants the caller relies on.anyhowin a library crate (outl-core,outl-md,outl-actions). Libraries usethiserrorso callers can match on variants.anyhowis only OK at binary boundaries (outl-cli,outl-tui).Box<dyn Error>as a public return type — same reason.Stringwhere&strworks,Vec<T>where&[T]works, owned arg where borrowed works — but only in public APIs and hot paths; do not bikeshed this on internal helpers.async fnwith a blocking call inside (std::fs,std::thread::sleep, large CPU loop withoutspawn_blocking).- Holding a
Mutex/RwLockacross an.await— deadlock waiting to happen. - Public API change on
outl-core,outl-md, oroutl-actionswithout doc-comment update — the per-crateCLAUDE.mdshould also reflect it.
Skip these (CI / fmt / clippy handle them):
- Import ordering, line width, brace placement.
- Naming conventions clippy already lints.
moddeclaration order.
Performance — hot paths only
Comment on performance only when the code is on a path that runs frequently or scales with workspace size. Do not flag allocations in setup, error paths, or one-shot CLI commands.
Paths that are hot in outl:
outl_core::tree— every op apply, every materialized-tree walk.outl_core::log— every append, every replay (workspace boot, sync pull).outl_md::parse/outl_md::render— every.mdread/write, every TUI refresh of a buffer.outl_md::index— backlink index rebuild scales with workspace size.outl_tuirender loop — runs on every keystroke.outl_actions::SyncEnginework loop — runs on every file event.
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 · 75 lines · 995 tokens per session scan A 0ff7ee36db6a
outl rust.instructions.md is an instructions file published in the GitHub repository outlmd/outl (161 stars, last pushed today), licensed MIT. It adds 995 tokens to every session, about $0.0050 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
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).