agent-reflectmem AGENTS.md

agent-reflectmem AGENTS.md is an instructions file for Codex, OpenCode from King-A23/agent-reflectmem. It costs 1,599 tokens per session, scanned A, original, MIT.

A repository guide for agent-reflectmem, a plugin bundle and Python tool that stores command outcomes and project rules in SQLite, a local database file. It describes the repository's current implementation and boundaries.

In plain words
What is it for?
Orienting an agent in the repository, including its sessions, command traces, rules, safety guards, wrappers, hooks, and tests.
Why use it?
It gives coding agents the project context needed to understand what already works and which fallback interfaces remain important.

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/king-a23/agent-reflectmem/agents-md
Clone the repo
git clone --depth 1 https://github.com/King-A23/agent-reflectmem

Made for: Codex, OpenCode.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for agent-reflectmem AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/king-a23/agent-reflectmem/agents-md.svg)](https://agentmods.dev/instructions/king-a23/agent-reflectmem/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/king-a23/agent-reflectmem/agents-md"><img src="https://agentmods.dev/badge/instructions/king-a23/agent-reflectmem/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,599 This file is loaded in full into every session.
When invoked 1,599 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 $0.01599 $0.01599
Opus 5 $0.00800 $0.00800
Sonnet 5 $0.00320 $0.00320
Haiku 4.5 $0.00160 $0.00160

Measured 3d ago against content hash ad8d4901ae1e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agent-reflectmem 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 3d 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.

AGENTS.md · 151 lines

How it starts

The opening of the file, as written. The whole thing — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent-ReflectMem Repository Guide

Project Summary

This repository contains:

  • a repo-local Codex plugin bundle
  • a reusable Python reflection engine
  • CLI and wrapper entrypoints that still work even if hook payloads drift

Agent ReflectMem captures failure -> retry -> success command loops, promotes durable project or environment rules, stores them in SQLite, and recalls them in later sessions or before related commands run again.

Current Status

Implemented and working:

  • session bootstrap and project fingerprinting
  • SQLite persistence for sessions, events, traces, rules, and audits
  • heuristic reflection and rule promotion
  • pre-action guard for related commands
  • rule conflict handling, decay, disable, trash, and verification
  • command sanitization before persistence
  • end-to-end wrapper and hook integration tests
  • signature coverage for Git safe-directory, service reachability, port conflicts, TLS, and version mismatch
  • guard modes for warn-only and require-confirm
  • installed cache/runtime drift validation against the repo copy

Important current boundary:

  • Codex hooks exist and are useful, but the fallback CLI and wrapper are still important.
  • Reflection is heuristic, not LLM-backed.
  • Hook failures are fail-open and logged to %LOCALAPPDATA%\AgentReflectMem\logs\codex-hook.log.

Repository Layout

Read the full file on GitHub · 151 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. 3d ago First seen · 151 lines · 1,599 tokens per session scan A ad8d4901ae1e

Subscribe to this mod's changes

agent-reflectmem AGENTS.md is an instructions file published in the GitHub repository King-A23/agent-reflectmem (1 stars, last pushed 3mo ago), licensed MIT. It adds 1,599 tokens to every session, about $0.0080 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