Borrowing it
Nothing to install: this file belongs to get-dst/dst. 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/get-dst/dst/main/CLAUDE.mdgit clone --depth 1 https://github.com/get-dst/dstWrote 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/get-dst/dst/claude-md)<a href="https://agentmods.dev/instructions/get-dst/dst/claude-md"><img src="https://agentmods.dev/badge/instructions/get-dst/dst/claude-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/get-dst/dst/claude-md"><img src="https://agentmods.dev/badge/instructions/get-dst/dst/claude-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 | $0.00804 | $0.00804 |
| Opus 5.5 | $0.00322 | $0.00322 |
| Sonnet 5.5 | $0.00161 | $0.00161 |
| Haiku 4.5 | $0.00080 | $0.00080 |
Grade A, and why
dst 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 21d 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 — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
dst — agent working rules
FastAPI + Postgres/pgvector backend (services/), React dashboard (apps/web/),
docs site (docs/ + mkdocs.yml). Commands: make dev (API :8000),
pnpm -C apps/web dev (:5173), make test, make lint, make migrate (runs
dst migrate; bare alembic does not sync the app role), make up (local Postgres).
This repository is public-ready, always
Every tracked file here is published as-is on release: the release overlays this tree onto the public repo whole, with no denylist. So:
- Commit only what a stranger may read. Plans, specs, strategy, experiments, benchmarks, blog drafts, marketing and customer or sandbox material live in the separate internal repo, never here, not even "temporarily".
- A blog post enters
docs/blog/posts/in the commit that publishes it. A file withdraft: truefailsmake ci. - A new top-level entry (or a new
docs/section) failstests/test_public_tree.pyuntil it is added to the allowlist there. Adding it is the moment to ask whether it is public. - Comments and docs explain the code to a reader; they never cite internal tickets, work items, test organizations, runs or people.
Concurrent agents: one writer per working tree
- The main checkout has one interactive writer at a time. Every other agent works in its own git worktree on its own branch, then merges when green.
- Stage surgically:
git diff <file>beforegit add <file>; nevergit add -A. A file with changes you did not make is another writer's work. - Every commit leaves a tree where
uv run python -c "import services.app"succeeds on a clean clone. - Expect main to move: pull/rebase before push; re-read files before editing.
- Plain commit messages saying what changed and why.
Gates
make cibefore every push (ruff check, ruff format --check, pytest with a database required, mypy fully clean, dashboard lint,.env.examplesync). Real exit codes: never gate on piped output.make ci-cleanbefore ending a session: clones committed HEAD and runs the suite from scratch.tests/test_live_auth_e2e.pyis opt-in viaDST_TEST_LIVE_E2E=1(needs Postgres, no API keys).
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.
- 21d ago First seen · 60 lines · 804 tokens per session scan A 9d0c6f3b08a3
dst CLAUDE.md is an instructions file published in the GitHub repository get-dst/dst (16 stars, last pushed today), licensed Apache-2.0. It adds 804 tokens to every session, about $0.0032 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 2026-09-26.
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.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.
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).