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/dmfaster/agents/agents-mdgit clone --depth 1 https://github.com/dmfaster/agentsWhat 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 | $0.00601 | $0.00601 |
| Opus 5 | $0.00300 | $0.00300 |
| Sonnet 5 | $0.00120 | $0.00120 |
| Haiku 4.5 | $0.00060 | $0.00060 |
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 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 — 65 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 1.0 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 1.0 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 a separate server-issued authorization bound to the exact campaign version after the owner approves it in DM Faster.
- Never add reply sending, meeting booking, provider-credential access, approval bypasses, or arbitrary workspace mutations.
- 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.
- yesterday 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 14d ago), licensed Apache-2.0. It adds 601 tokens to every session, about $0.0030 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 2026-08-31.
Other instructions, from other repositories
awesome-copilot-id AGENTS.md
Instructions for GulajavaMinistudio/awesome-copilot-id, covering communication, explanation and documentation, markdown formatting, user communication style and workflow & methodology.
hiveshare CLAUDE.md
Instructions for KB-perByte/hiveshare, covering hiveshare — claude.md, repo layout, build & run, key env vars (server) and naming: hive vs memory.
llm-safe-haven CLAUDE.md
Instructions for pleasedodisturb/llm-safe-haven, covering llm safe haven, what this is, project structure, tdd — non-negotiable (adopted 2026-08-17) and the contract.
kleosrules AGENTS.md
Instructions for kleosr/kleosrules, a project described as: Cursor harness pack: user rules, skills, Bash hooks, local HANDOFF memory. macOS, Linux, Windows (WSL).
coding-agent-safety-gate AGENTS.md
Instructions for ASER-ho/coding-agent-safety-gate, covering agents / 代理规则, 仓库类型 / repository type and ai 代理规则 / rules for ai coding agents.
yapcap CLAUDE.md
Claude Code instructions for TopiCsarno/yapcap, a project described as: Native COSMIC panel applet showing local usage limits for Codex, Claude Code, and Cursor.