Borrowing it
Nothing to install: this file belongs to Mte90/linus-torvalds-skill. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Mte90/linus-torvalds-skill/main/AGENTS.mdgit clone --depth 1 https://github.com/Mte90/linus-torvalds-skillWrote 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/mte90/linus-torvalds-skill/agents-md)<a href="https://agentmods.dev/instructions/mte90/linus-torvalds-skill/agents-md"><img src="https://agentmods.dev/badge/instructions/mte90/linus-torvalds-skill/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/mte90/linus-torvalds-skill/agents-md"><img src="https://agentmods.dev/badge/instructions/mte90/linus-torvalds-skill/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.01076 | $0.01076 |
| Opus 5.5 | $0.00430 | $0.00430 |
| Sonnet 5.5 | $0.00215 | $0.00215 |
| Haiku 4.5 | $0.00108 | $0.00108 |
Grade A, and why
linus-torvalds-skill AGENTS.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 1mo 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 — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — Project Conventions
Core Rules
- Generated Files: All
.mdartifacts are produced by scripts. Never edit them directly. See docs/CONTRIBUTING.md for the full regeneration table. - Git Discipline: Local-only git. No push/pull/rebase/merge. See docs/CONTRIBUTING.md.
- Language Agnosticism: Skills and souls must be language-agnostic. They capture Torvalds' METHOD, not his C knowledge.
- File Size Limit: Source files in
src/torvalds_skill/*must not exceed 900 lines. Split large modules into focused submodules. Grandfathered:report/build_comparison.py(1388),report/run_review.py(1308),report/classify_interviews.py(1161),report/comparison_render.py(932) — split ticket created, do not touch until that work is assigned. - No Committed Secrets: API keys, tokens, and credentials must never be hardcoded in source. All credentials come from environment variables (
OPENAI_API_KEY/REGOLO_API_KEY/LLM_API_KEYfor the key;OPENAI_BASE_URL/LLM_HOSTfor the endpoint). The.envfile is gitignored;.env.exampleis the template. If a key is ever committed, purge it from git history withgit filter-repobefore pushing. - Model Matching: No model-specific branching outside
src/torvalds_skill/profiles.py—get_profile()is the single source of truth. - Prompt Centralization: Prompt blocks live once in
src/torvalds_skill/distill_prompts.py; never duplicate across skills. - Trigger Contract: Pattern extraction regexes live in
report/trigger_patterns.py; consumed bybuild_comparison.pyandverify_skill.py. Change all three together. - Validation Symmetry: Both comparison arms must validate identically — either both run full checks or neither skips.
- Stats Generated: Pattern/word counts and timeouts come from
data/patterns.json; docs link to source, never type values. - Soul Generation: Soul files must be generated via the
soulCLI stage and validated withscripts/verify_soul.py, not hand-edited. Match skill variant (gpt-oss → soul.md, glm → soul-glm.md, mistral → soul-mistral.md, qwen → soul-qwen.md). - Caching: Unified cache is on by default (
CACHE_ENABLED=1). Bypass withCACHE_ENABLED=0. Cache entries expire afterCACHE_TTL_HOURS(default 168h / 7d). Cache path:CACHE_PATH(defaultdata/unified_cache.jsonl). Invalid cache = truncated responses never cached. - Profile Overrides: Priority: env vars > profiles.toml > built-in. Env format:
LLM_PROFILE_<NAME>__<FIELD>where dots and dashes in<NAME>become underscores (e.g.,LLM_PROFILE_GLM5_2__TIMEOUT=900forglm5.2,LLM_PROFILE_QWEN3_8_27B__TIMEOUT=900forqwen3.8-27b). TOML: copyprofiles.example.tomltoprofiles.toml.
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.
- 1mo ago Changed · +6 tokens per session 9f70c6fa57ff
- 1mo ago Changed · +58 tokens per session 1e59b838a735
- 1mo ago Changed · +15 lines · +422 tokens per session f948f775a40f
- 1mo ago Changed · +19 lines · +249 tokens per session 9ada561b44db
- 1mo ago Changed · +1 lines · +109 tokens per session 434e5cd61857
- 2mo ago First seen · 15 lines · 232 tokens per session scan A 214cc3f10e91
linus-torvalds-skill AGENTS.md is an instructions file published in the GitHub repository Mte90/linus-torvalds-skill (121 stars, last pushed 2d ago), licensed CC0-1.0. It adds 1,076 tokens to every session, about $0.0043 per session on Opus 5.5. 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
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.