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/wesleysimplicio/simplicio-loop/agents-mdgit clone --depth 1 https://github.com/wesleysimplicio/simplicio-loopWhat 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 | $0.03313 | $0.03313 |
| Opus 5 | $0.01656 | $0.01656 |
| Sonnet 5 | $0.00663 | $0.00663 |
| Haiku 4.5 | $0.00331 | $0.00331 |
Grade A, and why
simplicio-loop 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 — 193 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — simplicio-loop
Full map + step-by-step: docs/ECOSYSTEM_LLM_GUIDE.md · ADR 0009 · 0010
Max-speed LLM orientation (always): docs/LLM_MAX_SPEED_ORIENTATION.md — also re-fed every loop turn viaSIMPLICIO-LLM-ORIENTATIONin the loop skill.
Simplicio Ecosystem Contract (canonical)
This loop is the convergence layer of one Simplicio ecosystem. For every non-trivial task: run simplicio runtime map --repo . --for-llm markdown, then simplicio memory "<task>", rank/load relevant skills, execute through the native simplicio CLI, validate, and record evidence. MCP is fallback transport only.
Worker startup and centralized artifacts (mandatory)
Every subagent, worker, and provider session MUST read AGENTS.md, CLAUDE.md, and every relevant local skill before operating. For Loop work, the baseline skills are .claude/skills/simplicio-loop/SKILL.md, .claude/skills/simplicio-prism/SKILL.md, and .claude/skills/simplicio-runtime/SKILL.md; load additional satellite skills selected by the task before mutation.
The canonical default branch owns one centrally built binary/artifact set. Workers consume that binary read-only; they MUST NOT rebuild binaries or regenerate canonical Mapper/Fast artifacts. Worktrees isolate source edits and receipts only. Every receipt/handoff MUST record repository and revision, binary digest/version, Mapper generation and artifact digest. Missing, stale, incompatible, or mismatched central artifacts fail closed and route to the central rebuild path only; a worker may not repair them locally or fall back to fabricated/uncertified context.
Full-stack boundaries
simplicio-mapper / simplicio-dev-cli / simplicio-fast observe, plan, and edit — they work alone without Runtime. simplicio-runtime owns contracts, gates, validation, receipts, the full loop subsystem (activation + convergence authority), and mandatory execution-report metrics (per task + consolidated). Runtime alone decides when to activate the loop (simplicio loop decide). This package is the protocol + host-hook implementation under Runtime authority. Coordinators own cognition, not loop activation. See docs/adr/0009 and docs/adr/0010. Providers are workers, never authorities.
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 · 193 lines · 3,313 tokens per session scan A 185a64a23b72
simplicio-loop AGENTS.md is an instructions file published in the GitHub repository wesleysimplicio/simplicio-loop (2 stars, last pushed 2d ago), licensed MIT. It adds 3,313 tokens to every session, about $0.0166 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
ClawRouter CLAUDE.md
Instructions for BlockRunAI/ClawRouter, covering clawrouter, commands, project structure, key dependencies and conventions.
SearChat CLAUDE.md
Claude Code instructions for yokingma/SearChat, covering claude.md, project overview, architecture, monorepo structure and key technologies.
codex-autoresearch AGENTS.md
Instructions for TheGreenCedar/codex-autoresearch, covering agents.md, purpose and scope, canonical sources, stable product boundaries and source and package boundaries.
ai AGENTS.md
AGENTS.md instructions for vercel/ai, covering agents.md, project overview, repository structure, key directories and core package dependencies.
InvestSkill GEMINI.md
Instructions for yennanliu/InvestSkill, covering investskill — gemini cli setup & usage guide, installation & setup, quick start, navigate to the investskill directory and start gemini cli (loads gemini.md automatically).
DevoxxGenieIDEAPlugin GEMINI.md
Instructions for devoxx/DevoxxGenieIDEAPlugin, a project described as: DevoxxGenie is an agentic plugin for IntelliJ IDEA that uses local LLM's (Ollama, LMStudio, GPT4All, Jan and Llama.cpp) and Cloud based LLMs to help review, test, explain your project code. Latest version now also supports Spec Driven Development…