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/entropy-cloud/attractor-guided-engineering-template/agents-mdgit clone --depth 1 https://github.com/entropy-cloud/attractor-guided-engineering-templateWhat 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 | $0.02830 | $0.02830 |
| Opus 5 | $0.01415 | $0.01415 |
| Sonnet 5 | $0.00566 | $0.00566 |
| Haiku 4.5 | $0.00283 | $0.00283 |
Grade A, and why
attractor-guided-engineering-template 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 2d 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 — 191 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Project Intent
mission-driver (self-hosting AGE workspace) uses a lightweight Attractor-Guided Engineering workflow for AI-assisted application development.
This repository is for an application-layer product, not a framework-core project.
The repo is the source of truth. Chat is only a temporary working surface.
Dual-Audience Repo
This repository serves two audiences:
- As a real project — it develops
tools/mission-driver/(a Node.js Flow DSL engine + Vue 3 monitor dashboard) using its own AGE workflow. The repo dogfoods its own methodology. - As a template — consumers run
./install-age.sh /path/to/target "Project Name"from a clone of this repo. The installer copies a curated file set listed ininstall-age.manifest(sourcing fill-in files fromtemplate/and shared methodology guides from repo root) into a new project root, then auto-creates the mission-driver shim,.env,missions/base.json,docs/logs/{year}/, and.gitignore.
Files at the repo root and under docs/ are the REAL PROJECT versions (filled in for mission-driver development). Pristine template versions of fill-in files live under template/. For the manual fallback flow (no bash), see template/START-HERE-after-copy.md; for the primary automated flow, run ./install-age.sh and read its NEXT STEPS output.
In-Tree Tool
tools/mission-driver/ is a real, in-tree Node.js tool — NOT a scaffold example. It is the engine that automates this repo's own AGE loop. Read tools/mission-driver/CONTEXT.md for the 30-second overview. It is attached as subdirectory context when you read files under tools/mission-driver/.
Before writing non-trivial code, agents must first understand:
docs/context/project-context.mddocs/context/ai-autonomy-policy.mddocs/context/codebase-map.md- the requirement or owner doc (under
docs/requirements/ordocs/design/) that describes the work's intended behavior — current work-in-progress is read from unfinished plans indocs/plans/, not from a field inproject-context.md - the relevant raw inputs under
docs/input/when requirement meaning depends on source material
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.
- 2d ago First seen · 191 lines · 2,830 tokens per session scan A 02c835474450
attractor-guided-engineering-template AGENTS.md is an instructions file published in the GitHub repository entropy-cloud/attractor-guided-engineering-template (74 stars, last pushed 3d ago), licensed MIT. It adds 2,830 tokens to every session, about $0.0141 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
skills AGENTS.md
Instructions for open-mercato/skills, covering agent instructions, task routing, skill authoring standards, validation and conventions.
dev-skills CLAUDE.md
Claude Code instructions for sungurerdim/dev-skills, covering dev-skills, meta, project structure, skills (30) and development.
SpecRoute CLAUDE.md
Instructions for Enovatr-Labs/SpecRoute, a project described as: Open source framework for spec-driven agentic software engineering. PRDs, prompts, agents, skills, workflows, and coding rules for Codex, Claude, and modern AI development teams.
agent-skills CLAUDE.md
Instructions for dmythro/agent-skills, a project described as: Agent skills for OpenCode, Claude Code and other AI agents.
map-framework CLAUDE.md
Instructions for azalio/map-framework, covering map framework (mapify-cli) — agent instructions, what this repo is, critical invariant: template single-source render, skill catalog invariant and how to work in this repo.
cctop AGENTS.md
Instructions for st0012/cctop, covering agents.md - development guide for cctop, scope and sources, required development rules, driver workflow and github and pr rules.