revrem AGENTS.md

Repository instructions for a code-review automation project that uses Meminit, a tool for managing controlled project documents.

In plain words
What is it for?
Setting up and checking project documents, preserving required progress output, and keeping changes portable and free of secrets.
Why use it?
They define rules for code, documentation, tests, dependencies, generated files, and safe use of the automation loop.

Instructions file for CodexOpenCode

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/gitcmurf/revrem/agents-md
Clone the repo
git clone --depth 1 https://github.com/GitCmurf/revrem

Made for: Codex, OpenCode.

Per session 358 This file is loaded in full into every session.
When invoked 358 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 $0.00358 $0.00358
Opus 5 $0.00179 $0.00179
Sonnet 5 $0.00072 $0.00072
Haiku 4.5 $0.00036 $0.00036

Measured yesterday against content hash 921e929d1c7c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

revrem 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.

AGENTS.md · 33 lines

What it actually says

Agentic Coding Rules

This repository (code-review-loop) uses Meminit DocOps for governance.

Using Meminit

Run meminit commands to create and manage governed documents:

  • meminit init — initialize DocOps (run once)
  • meminit new <TYPE> <TITLE> — create a new governed document
  • meminit check — verify compliance
  • meminit doctor — diagnose repo readiness

Document IDs follow REVREM-TYPE-SEQ (e.g., REVREM-ADR-001).

Project Rules

  • The atomic unit of work is code + documentation + tests.
  • Keep the runtime dependency-free unless a dependency removes clear operational risk. tomli-w is an accepted exception: it eliminates an entire class of TOML encoding bugs (surrogate escapes, escaping edge cases) that would be fragile to maintain by hand.
  • Preserve operator-visible progress and artifact output; this tool is for watched local automation.
  • Keep nested Codex execution bounded by default. Any unbounded mode must be explicit.
  • Prefer portable POSIX/Linux behavior and avoid shell-specific assumptions in Python code.
  • Never commit secrets, local Codex transcripts, or generated loop artifacts.

Rules

  • Never modify a document_id once set.
  • Always use meminit new to create governed documents.
  • All code changes must include documentation and tests.
  • Never commit secrets or PII.
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 · 33 lines · 358 tokens per session scan A 921e929d1c7c

Subscribe to this mod's changes

revrem AGENTS.md is an instructions file published in the GitHub repository GitCmurf/revrem (1 stars, last pushed 16d ago), licensed Apache-2.0. It adds 358 tokens to every session, about $0.0018 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.