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/copilot-instructionsgit 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 | $0.02539 | $0.02539 |
| Opus 5 | $0.01269 | $0.01269 |
| Sonnet 5 | $0.00508 | $0.00508 |
| Haiku 4.5 | $0.00254 | $0.00254 |
Grade A, and why
outl 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 yesterday.
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 — 210 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Copilot review instructions — outl
You are reviewing a pull request in outl, a local-first outliner with a CRDT-based tree sync engine, written in Rust. Read this whole file before commenting. Your job is not a style pass — fmt, clippy, and CI already enforce style. Your job is the review a Staff/Principal engineer would give: catch correctness, architecture, and scalability problems that humans miss, and only speak when it matters.
If you cannot map a finding to a concrete, real-world consequence, stay silent. Noise costs reviewer attention; a single sharp comment earns trust.
0. Read these first
- Root
CLAUDE.md— project-wide invariants and conventions. - The
CLAUDE.mdinside the crate(s) the PR touches (e.g.crates/outl-core/CLAUDE.md). CONTRIBUTING.md— the merge bar and "decisions you don't get to revisit".docs/contributing.md— the review policy this file mirrors.docs/development.md— the engineer onramp (build / run / test / debug / CI / release). Load it when the PR touches CI workflows, slash commands, hooks, agents, or anything else a contributor's first 30 minutes depend on.docs/architecture.md,docs/crdt.md,docs/markdown-format.md— load the relevant one when the PR touches that area.- The PR description and any linked issue.
Treat the per-crate CLAUDE.md as authoritative over generic Rust opinions.
If your suggestion contradicts it, drop the suggestion.
Where the rest of this lives
This file is deliberately short — GitHub recommends repository-wide instructions stay within about two pages, and everything below applies only to certain paths.
Copilot loads these in addition to this file whenever a changed file matches their applyTo glob, so a Rust PR gets the Rust bar without a Solid PR paying for it.
| File | applyTo |
Carries |
|---|---|---|
instructions/rust.instructions.md |
**/*.rs |
Rust quality bar, hot-path performance rules, testing bar |
instructions/shared-primitives.instructions.md |
crates/** |
The shared primitives catalog — check before approving any new helper |
instructions/architecture.instructions.md |
crates/** |
Reuse-first violations, documentation-drift blocking |
instructions/markdown.instructions.md |
**/*.md |
Semantic line breaks, one owner per fact |
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.
- yesterday First seen · 210 lines · 2,539 tokens per session scan A 05990554557a
outl copilot-instructions.md is an instructions file published in the GitHub repository outlmd/outl (161 stars, last pushed yesterday), licensed MIT. It adds 2,539 tokens to every session, about $0.0127 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
firecrawl CLAUDE.md
Claude Code instructions for firecrawl/firecrawl: Firecrawl is a web scraper API. The directory you have access to is a monorepo.
siyuan AGENTS.md
AGENTS.md instructions for siyuan-note/siyuan, covering agents.md, 1. non-negotiable constraints, do not hand-edit, verification and prohibited operations and 2. project-specific rules.
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.
kipi-system AGENTS.md
AGENTS.md instructions for assafkip/kipi-system, covering q entrepreneur os, project structure, conventions, commands and build and test.
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).