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/claude-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 | $0.03230 | $0.03230 |
| Opus 5 | $0.01615 | $0.01615 |
| Sonnet 5 | $0.00646 | $0.00646 |
| Haiku 4.5 | $0.00323 | $0.00323 |
Grade A, and why
simplicio-loop CLAUDE.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 — 206 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — simplicio-loop (Claude Code)
This repo ships simplicio-loop, a runtime-agnostic super-plugin: an autonomous
looping orchestrator (the /simplicio-loop skill) plus six satellite skills, packaged for 12
runtimes.
The 7 skills
| Skill | Role |
|---|---|
simplicio-loop |
unified public entrypoint: orchestrator core + hardened Ralph loop — re-feed the goal until an evidence-gated <promise> or a cap; durable run-journal (attempt memory) + stall detector (scripts/loop_journal.py) so it switches strategy instead of oscillating, plus a task anchor (scripts/task_anchor.py) — durable memory for SCOPE that freezes the acceptance criteria and blocks drift / "done" while any AC is unverified — and, above it, a task backlog (scripts/task_backlog.py, SKILL.md § Phase 0): the frozen multi-item LLM decomposition (per-item ACs + depends_on), genesis-aware (an empty repo leads with a scaffold item), whose done is gated on the verified anchor |
simplicio-tasks |
legacy alias kept only for compatibility with older installs and saved prompts |
simplicio-orient |
terminal-first token economy — output-reduction catalog, tee-cache, signatures-read |
simplicio-review |
thermos-style parallel adversarial review on distinct rubrics → deduped verdict |
simplicio-compress |
caveman-style prose + memory compression, byte-preserving, transform_guard |
simplicio-learn |
retrospective → durable, deduped lessons written to memory |
simplicio-autoresearch |
evolutionary mutate/eval/keep-revert optimizer (Karpathy autoresearch) — yool-guardrailed caps, git-isolated branch, anti-Goodhart gate-first eval, savings-event receipt (scripts/autoresearch.py) |
They live in .claude/skills/ and load automatically in this repo.
The 2 bound operators (REQUIRED by the loop)
simplicio-loop does not survey or edit with the LLM — it delegates to two installed CLIs. The
supported install surface is the single package simplicio-cli, which exposes
simplicio-dev-cli and also brings simplicio-mapper transitively; the loop BLOCKS if either
runtime binary is absent:
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 · 206 lines · 3,230 tokens per session scan A b23978434767
simplicio-loop CLAUDE.md is an instructions file published in the GitHub repository wesleysimplicio/simplicio-loop (2 stars, last pushed 2d ago), licensed MIT. It adds 3,230 tokens to every session, about $0.0161 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
Claude Code 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.
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…
aisix CLAUDE.md
Instructions for api7/aisix, covering claude.md, 1. think before coding, 2. simplicity first, 3. surgical changes and 4. goal-driven execution.