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/mountainunicorn/add/agents-mdgit clone --depth 1 https://github.com/MountainUnicorn/addWhat 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 | $0.00462 | $0.00462 |
| Opus 5 | $0.00231 | $0.00231 |
| Sonnet 5 | $0.00092 | $0.00092 |
| Haiku 4.5 | $0.00046 | $0.00046 |
Grade A, and why
add 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.
What it actually says
ADD
ADD (Agent Driven Development) solves this by bringing structured, specification-driven SDLC practices to AI-native development—just as TDD revolutionized testing and DDD revolutionized domain modeling, ADD provides a proven methodology for human-AI collaboration at scale.
Engagement Protocol
The human is the architect and decision maker; the agent is the builder. Gather requirements via one-question-at-a-time interviews. Never batch questions. When stepping away, declare autonomy ceilings explicitly — the agent may climb local → dev → staging but never merges to main or ships to production without human approval.
Spec-First Invariants
Every feature flows through the document hierarchy: PRD → Feature Spec → Implementation Plan → User Test Cases → Automated Tests → Implementation. No link may be skipped. Specs live in specs/, plans in docs/plans/. Code changes without a corresponding spec are rejected on review.
Maturity & Autonomy Ceiling
Project maturity: beta.
- local: auto-promotion not declared.
Production deploys and merges to the default branch always require human approval.
Currently Active Spec
None in flight. Last shipped: specs/codex-agent-prefixing.md (v0.11.0), specs/init-defaults.md, specs/doctor.md, specs/codex-install-manifest.md (v0.10.2). Current focus: GA promotion (docs/milestones/v1.0-ga.md) — marketplace approval pending.
Pointers
.add/config.json— project configurationdocs/prd.md— product requirementsspecs/— feature specificationscore/rules/— behavioral rules (ADD-managed projects)
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 · 35 lines · 462 tokens per session scan A 339832eb2a8f
add AGENTS.md is an instructions file published in the GitHub repository MountainUnicorn/add (11 stars, last pushed 1mo ago), licensed MIT. It adds 462 tokens to every session, about $0.0023 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
portable-dev-system CLAUDE.md
Claude Code instructions for rmzi/portable-dev-system, covering portable development system, plugin architecture, workflow, rule and user-facing voice.
superpowers GEMINI.md
Gemini CLI instructions for obra/superpowers, a project described as: An agentic skills framework & software development methodology that works.
no-vibe AGENTS.md
Instructions for rizukirr/no-vibe, covering agents, repo purpose, architecture (high-signal files), verification commands and conventions that are easy to miss.
cortex CLAUDE.md
Claude Code instructions for alphaaiservice/cortex, covering claude.md — cortex plugin development context, what is this project?, plugin architecture, directory structure and how each component works.
pamplejuce AGENTS.md
Instructions for sudara/pamplejuce, a project described as: A JUCE audio plugin template. JUCE 8, Catch2, Pluginval, macOS notarization, Azure Trusted Signing, Github Actions.
openclaw-mcp-bridge CLAUDE.md
Instructions for gabrielekarra/openclaw-mcp-bridge, covering claude.md, project overview, build & development commands, architecture and key dependencies.