Borrowing it
Nothing to install: this file belongs to dmfaster/agents. 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/dmfaster/agents/main/AGENTS.mdgit clone --depth 1 https://github.com/dmfaster/agentsWrote 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/dmfaster/agents/agents-md)<a href="https://agentmods.dev/instructions/dmfaster/agents/agents-md"><img src="https://agentmods.dev/badge/instructions/dmfaster/agents/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/dmfaster/agents/agents-md"><img src="https://agentmods.dev/badge/instructions/dmfaster/agents/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 | $0.01264 | $0.01264 |
| Opus 5.5 | $0.00506 | $0.00506 |
| Sonnet 5.5 | $0.00253 | $0.00253 |
| Haiku 4.5 | $0.00126 | $0.00126 |
Grade A, and why
agents 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 7d 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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DM Faster public agent source
This repository contains only the public DM Faster Agent 2.0 API contract, local authentication library, SDK, CLI, MCP server, portable campaign UI, and shared Codex, Claude, and Cursor plugin.
Task and tool routing
- Repository development is the default mode in this checkout. Use source, contract tests, package tests, and local diagnostics for implementation, review, and release work.
- Do not invoke the DM Faster skill, MCP server, or CLI merely because a repository task mentions campaigns, replies, sending, pipeline, or companies. Those interfaces operate a user's live workspace; they are not development tools.
- Use live DM Faster tools only when the user explicitly requests current workspace evidence or an approved end-to-end test targets the public interface.
- Treat mixed prompts that ask to fix a product symptom as repository tasks first. Live observations supplement source evidence; they never replace it.
Commands
- Use Node.js 24.
- Install with
npm ci. - Run
npm run check:agentsfor the complete contract, MCP protocol, build, package, clean-install, type, and unit test suite. - Run
npm audit --omit=devbefore release.
Source of truth
- Change
packages/public-api/openapi.yaml, then runnpm run generate:agent-api. - Keep all four published package versions, all three plugin manifest versions, and every version-pinned command identical.
packages/product-uiis a private build-only workspace used to generate the self-contained MCP Apps resource; it must never be published.- Keep the canonical skill under
plugins/dmfaster/skills/dmfaster/. - Keep repository-wide coding-agent instructions in this file. Root
CLAUDE.mdimports it rather than duplicating policy. - Never add DM Faster application, database, extension, browser-worker, cookie, or private-repository dependencies.
Agent 2.0 boundary
- Planning and inspection tools are bounded reads.
- List and campaign preparation may create only private, disabled drafts and must remain idempotent.
- Launch and pause require an explicit user instruction and a server-issued
authorization bound to the exact campaign version. An owner may grant
campaigns:controlonce during browser connection so preflight returnsreadywithout per-action approval. Existing connections retain their original per-action browser approval contract; never upgrade credentials silently. - Inbox replies require the user's explicit instruction for the exact text and inspected conversation. Use a durable idempotency key, retain the app's provider/role checks, and report queued delivery separately from confirmed sending. A previously granted connection permission plus that instruction must not acquire a second approval screen solely because an agent calls it.
- Pipeline stage and note writes, and follow-up cancellation, require exact inspected identities and conflict checks. Never infer a booked meeting from a queued message or a positive reply alone.
- Calendar booking sends invitations only for exact user-instructed details, with owner calendar grants and a durable immutable request key. Preserve app availability checks and distinguish observed free slots from a booked event.
- Never expose provider credentials, bypass consent, or add arbitrary workspace mutations. New controls must have typed, bounded contracts and matching Product implementation.
- Exact audience totals are invariant. Never substitute a lower bound, sample, estimate, or guessed count.
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.
- 7d ago Changed · +12 lines · +459 tokens per session 38347c431c33
- 1mo ago Changed · +3 lines · +42 tokens per session ad55cc96652d
- 1mo ago Changed · +9 lines · +119 tokens per session f0183690cad5
- 1mo ago Changed · +3 lines · +43 tokens per session 36719a4d6a6f
- 2mo ago First seen · 65 lines · 601 tokens per session scan A 2538583063d4
agents AGENTS.md is an instructions file published in the GitHub repository dmfaster/agents (0 stars, last pushed 2d ago), licensed Apache-2.0. It adds 1,264 tokens to every session, about $0.0051 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 2026-08-31.
Other instructions, from other repositories
plugin-files-mode
Rosetta Plugin Mode Bootstrap.
md-feedback copilot-instructions.md
Copilot instructions for yeominux/md-feedback, covering plan review workflow, before implementing any plan, annotation types and mcp setup.
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.