agent-recall-trail AGENTS.md

agent-recall-trail AGENTS.md is an instructions file for Codex, OpenCode from fantasyce/agent-recall-trail. It costs 181 tokens per session, scanned A, original, Apache-2.0.

Project instructions for Agent Recall Trail, a system for private agent memory and human-reviewed shared knowledge.

In plain words
What is it for?
Following the project’s test-driven development process, maintaining separate SQLite memory files, and avoiding unsafe data or unrelated configuration changes.
Why use it?
They give developers rules for testing, separating memory from published knowledge, protecting secrets, and keeping agent identities isolated.

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/fantasyce/agent-recall-trail/agents-md
Clone the repo
git clone --depth 1 https://github.com/fantasyce/agent-recall-trail

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-recall-trail AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/fantasyce/agent-recall-trail/agents-md.svg)](https://agentmods.dev/instructions/fantasyce/agent-recall-trail/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/fantasyce/agent-recall-trail/agents-md"><img src="https://agentmods.dev/badge/instructions/fantasyce/agent-recall-trail/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 181 This file is loaded in full into every session.
When invoked 181 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 $0.00181 $0.00181
Opus 5 $0.00090 $0.00090
Sonnet 5 $0.00036 $0.00036
Haiku 4.5 $0.00018 $0.00018

Measured 3d ago against content hash 5383a1a9a5b9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agent-recall-trail 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 · 11 lines

What it actually says

ART development contract

  • The current design and implementation plans under docs/specs/ and docs/plans/ are the product and acceptance contracts.
  • Use test-driven development. Observe each new behavior test fail before implementing it.
  • Keep every Agent Vault in a physically distinct SQLite file and bind MCP identity at process start.
  • Memory and published knowledge are different object families. Agents never approve or publish knowledge.
  • Do not read, copy, translate, or structurally imitate competitor source code, schemas, prompts, tests, names, or directory layouts.
  • Tests use an explicit task-owned ART_HOME; never write test data to the formal ~/.across runtime.
  • Do not modify unrelated products, existing knowledge sources, or formal Codex/DSH configuration during automated tests.
  • Do not persist secrets, full transcripts, unrestricted command output, or recalled bundle bodies.
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 · 11 lines · 181 tokens per session scan A 5383a1a9a5b9

Subscribe to this mod's changes

agent-recall-trail AGENTS.md is an instructions file published in the GitHub repository fantasyce/agent-recall-trail (0 stars, last pushed 3d ago), licensed Apache-2.0. It adds 181 tokens to every session, about $0.0009 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.