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/second-order-systems/dystil/agents-mdgit clone --depth 1 https://github.com/Second-Order-Systems/DystilWrote 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/second-order-systems/dystil/agents-md)<a href="https://agentmods.dev/instructions/second-order-systems/dystil/agents-md"><img src="https://agentmods.dev/badge/instructions/second-order-systems/dystil/agents-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 | $0.01950 | $0.01950 |
| Opus 5 | $0.00975 | $0.00975 |
| Sonnet 5 | $0.00390 | $0.00390 |
| Haiku 4.5 | $0.00195 | $0.00195 |
Grade A, and why
Dystil 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 4d 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 — 184 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Instructions for coding agents working in this repository. Humans are welcome to read it too — it is the fastest orientation available.
What Dystil is
A local-first desktop app that observes how you work, identifies work that repeats, and produces reusable instructions that can do that work again. The user-facing loop is Worth fixing (repetitive work found, with evidence) → Ask for fix (the user clarifies) → Ready to use (kept, reusable artifacts).
It is not a note-taking app, a day planner, or a chatbot over your history.
Source of truth — read this before trusting any document
Precedence, highest first:
- The code. Always wins.
agent_docs/— verified against the code, and every factual claim carries a citation. Trust it, but if a citation no longer resolves, the document is wrong; fix it or file it.- Everything else —
public_docs/,README.md, marketing copy.
public_docs/ is positioning, not specification. It describes what Dystil is
for and where it is going, and it is deliberately allowed to run ahead of the code.
It may use explanatory concepts (for example "work cards") that do not correspond to
any type in the codebase.
- Never implement from
public_docs/. - Never cite it in review.
- Never treat a capability named there as existing.
If narrative and engineering disagree, engineering is right. If engineering and the code disagree, the code is right — and the document is a bug.
Why this exists: an earlier
docs/TECHNICAL_ARCHITECTURE.mdconfidently described a bundledllama.cppruntime, named models, fixed ports, embeddings, and vector search. None of it existed. It read exactly like a real engineering reference, and it propagated into the README. Assume any uncited document is capable of the same.
Writing docs
- A claim in
agent_docs/needs a citation: path + symbol name or a short verbatim quote. Neverpath:line— line numbers drift and break the check. Good:app_config.rs :: telemetry_endpoint()orCargo.toml — `enterprise-client = ["cloud-sync", "official-build"]` public_docs/must contain no falsifiable specifics — no ports, model names, schemas, crate names, file paths, or sizes. If it can be wrong, it belongs inagent_docs/.- Every doc carries a
status:in its frontmatter. Three values:
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.
- 4d ago First seen · 184 lines · 1,950 tokens per session scan A dbd9b0193694
Dystil AGENTS.md is an instructions file published in the GitHub repository Second-Order-Systems/Dystil (24 stars, last pushed 10d ago), licensed Apache-2.0. It adds 1,950 tokens to every session, about $0.0097 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 2026-08-30.
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).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
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 oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.