Memory-Recall AGENTS.md

Memory-Recall AGENTS.md is an instructions file for Codex, OpenCode from rebel0789/Memory-Recall. It costs 1,577 tokens per session, scanned A, original, Apache-2.0.

AGENTS.md instructions for rebel0789/Memory-Recall, covering agents.md — operating manual for coding agents, mission, read order before changing code, current reality and implemented as a reference bootstrap.

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/rebel0789/memory-recall/agents-md
Clone the repo
git clone --depth 1 https://github.com/rebel0789/Memory-Recall

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 Memory-Recall AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/rebel0789/memory-recall/agents-md.svg)](https://agentmods.dev/instructions/rebel0789/memory-recall/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/rebel0789/memory-recall/agents-md"><img src="https://agentmods.dev/badge/instructions/rebel0789/memory-recall/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,577 This file is loaded in full into every session.
When invoked 1,577 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 $0.01577 $0.01577
Opus 5 $0.00788 $0.00788
Sonnet 5 $0.00315 $0.00315
Haiku 4.5 $0.00158 $0.00158

Measured today against content hash b76296853d5c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Memory-Recall 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 today.

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 · 186 lines

How it starts

The opening of the file, as written. The whole thing — 186 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — Operating Manual for Coding Agents

Mission

Develop Memory Recall into the local-first, model-neutral repository memory and context tool for coding agents. Optimize for correctness, evidence, portability, and safe evolution, not feature count or autonomous behavior.

Read order before changing code

  1. ASSIGN_TO_AGENT.md
  2. PROJECT_STATUS.json
  3. PRODUCT.md
  4. DESIGN.md for UI work
  5. docs/architecture/overview.md
  6. nearest directory-level AGENTS.md
  7. relevant schema in packages/protocol/schemas/
  8. task bundle from npm run task -- <OAF-ID>
  9. relevant threat-model section

Do not load all research notes or every skill into context. Retrieve only what the task needs.

Current reality

Implemented as a reference bootstrap

  • local HTTP control API,
  • responsive static product shell,
  • file-backed local state and append-only run event projection,
  • Context Compiler and deterministic model gateway,
  • cancellable embedded workflow runner with event checkpoints,
  • policy, evidence, memory-write, and tool-registry primitives,
  • native SQLite/FTS5 memory and content-addressed artifact providers,
  • optional loopback-only Ollama provider,
  • portable Agent Packs, safe replay plans, and learning proposals,
  • provider ports and disabled integration conformance fixtures,
  • synthetic Content Intelligence workflow,
  • tests, protocol compatibility fixtures, and evaluations.

Specified but pending

  • PostgreSQL runtime store,
  • durable workflow adapter,
  • production authentication,
  • real network connectors,
  • external publishing,
  • production frontend framework,
  • signed adapter and skill distribution.

Never describe a specified feature as implemented. Check PROJECT_STATUS.json.

Commands

npm run bootstrap
npm run status
npm run task -- <OAF-ID>
npm run dev
npm run demo
npm run protocol:validate
npm run native:smoke
npm test
npm run eval
npm run check
npm run ci

Agent skills

Issue tracker

Issues are tracked in GitHub Issues for rebel0789/Memory-Recall; local markdown under .scratch/ may be used for offline or scratch drafts. External PRs are a triage surface. See docs/agents/issue-tracker.md.

Read the full file on GitHub · 186 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. today First seen · 186 lines · 1,577 tokens per session scan A b76296853d5c

Subscribe to this mod's changes

Memory-Recall AGENTS.md is an instructions file published in the GitHub repository rebel0789/Memory-Recall (8 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 1,577 tokens to every session, about $0.0079 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 2026-09-04.