simplicio-loop GEMINI.md

A runtime-independent set of instructions for running the simplicio-loop workflow with coding agents such as Gemini, Codex, Copilot, Grok, or local agents.

In plain words
What is it for?
Use it to inspect repository guidance, run simplicio mapping and planning commands, make an issue-scoped change, and verify it with tests or other project checks.
Why use it?
It gives the agent a defined order for understanding the repository, planning a bounded change, editing files, and checking the result. This reduces guesswork when handling open issues.

Instructions file for Gemini CLI

Install

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.

agentmods
npx agentmods add instructions/wesleysimplicio/simplicio-loop/gemini-md
Clone the repo
git clone --depth 1 https://github.com/wesleysimplicio/simplicio-loop

Made for: Gemini CLI.

Per session 1,107 This file is loaded in full into every session.
When invoked 1,107 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What 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.

ModelPer sessionOnce invoked
Fable 5 $0.01107 $0.01107
Opus 5 $0.00553 $0.00553
Sonnet 5 $0.00221 $0.00221
Haiku 4.5 $0.00111 $0.00111

Measured yesterday against content hash 643f9152b5c4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

simplicio-loop GEMINI.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.

GEMINI.md · 99 lines

How it starts

The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.

GEMINI.md — simplicio-loop (Gemini / other runtimes)

The simplicio-loop skill is runtime-agnostic. Gemini, Codex, Copilot, Grok, or any local agent can run it from the same source file.

Load

Point your agent at:

.claude/skills/simplicio-loop/SKILL.md

The folder name is .claude/ for convention, but nothing in the skill is Claude-specific — it uses only shell, git, gh, file edit, and web.

Use

simplicio-loop: finish all the open issues

Current flow for any LLM

Read llms.txtAGENTS.md.claude/skills/simplicio-loop/SKILL.md. Check simplicio-mapper --help, simplicio-fast --help, and simplicio-dev-cli --help; then run Mapper scan, inspect, and handoff before deciding an AC-scoped change. Use Fast for bounded snapshot/PlanDAG context, Dev CLI for the edit plus verification, and real tests/gates for evidence. Runtime/MCP is off by default (standalone); do not invoke it unless explicitly opted in.

The orchestrator delegates, when loaded, to five satellite skills — simplicio-loop (Ralph loop), simplicio-orient (terminal-first token economy), simplicio-review (adversarial review), simplicio-compress (prose + memory compression), simplicio-learn (retrospective). All live in .claude/skills/.

Install & token economy

bash scripts/install.sh gemini      # writes .gemini/settings.json MCP + loads the skills
python3 hooks/orient_clamp.py -- <heavy command>   # reduce output before it hits context

Binding

Use the host-independent bounded delivery policy and its ADR 0008 for WIP, frozen scope, reviews, ownership, integration, and release boundaries.

Where your runtime exposes native capabilities (a repo mapper, a deterministic file writer, a local model fan-out, a durable scheduler), bind them to the matching extension points in the Step 1b table so the steps become deterministic and near-zero-token. Otherwise the LLM fallbacks cover 100% of the work.

Read the full file on GitHub · 99 lines

Changes

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.

  1. yesterday First seen · 99 lines · 1,107 tokens per session scan A 643f9152b5c4

Subscribe to this mod's changes

simplicio-loop GEMINI.md is an instructions file published in the GitHub repository wesleysimplicio/simplicio-loop (2 stars, last pushed 2d ago), licensed MIT. It adds 1,107 tokens to every session, about $0.0055 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.

Related

Other instructions, from other repositories