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.
npx agentmods add instructions/zhangtian-123/codex-memory/agents-mdgit clone --depth 1 https://github.com/zhangtian-123/codex-memoryWrote 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.
[](https://agentmods.dev/instructions/zhangtian-123/codex-memory/agents-md)<a href="https://agentmods.dev/instructions/zhangtian-123/codex-memory/agents-md"><img src="https://agentmods.dev/badge/instructions/zhangtian-123/codex-memory/agents-md.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00269 | $0.00269 |
| Opus 5 | $0.00134 | $0.00134 |
| Sonnet 5 | $0.00054 | $0.00054 |
| Haiku 4.5 | $0.00027 | $0.00027 |
Grade A, and why
codex-memory 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 4d 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.
What it actually says
Repository Guidelines
This repository implements a local Markdown-backed memory service for agent workflows. Keep source, tests, synthetic examples, and public documentation in this repository.
Source Boundaries
- Do not commit real memory vaults, transcript files, derived indexes, local hook candidates, report exports, virtual environments, or build output.
- Keep examples synthetic and safe to publish.
- Treat
.index/data as rebuildable output. - Keep local machine paths out of committed documentation and tests unless they
are generic examples such as
~/.codex/memories.
Validation
For Python changes, run:
PYTHONPATH=src python3 -m unittest discover -s tests
For Rust keyword-helper changes, run:
cd rust/codex-memory-keyword
cargo test
For hook behavior changes, update or add transcript-level regression tests in
tests/test_cli_hooks.py. For retrieval or hygiene changes, update focused
coverage in tests/test_markdown_store.py or tests/test_maintenance.py.
Public Release Hygiene
Before publishing a branch or archive, run a sensitive-string scan for private paths, project names, customer names, and transcript/vault content. The public repository should contain code plus synthetic examples only.
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.
- 4d ago First seen · 40 lines · 269 tokens per session scan A ac946ac7c00e
codex-memory AGENTS.md is an instructions file published in the GitHub repository zhangtian-123/codex-memory (0 stars, last pushed 2mo ago), licensed MIT. It adds 269 tokens to every session, about $0.0013 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.
Other instructions, from other repositories
cognirepo CLAUDE.md
Claude Code instructions for ashlesh-t/cognirepo, covering claude.md, key rules, session start sequence (run in this order), behavioral confirmation rule and personas (cognirepo-402, cognirepo-403).
aeon CLAUDE.md
Claude Code instructions for aeonfun/aeon, covering aeon, how aeon works, strategy, voice and soul file hierarchy (read in this order).
wayland-core copilot-instructions.md
Copilot instructions for FerroxLabs/wayland-core, covering ijfw rules, output discipline, memory routing, context discipline and cross-audit.
mcp-structured-memory CLAUDE.md
Claude Code instructions for nmeierpolys/mcp-structured-memory, a project described as: Structured Memory MCP Server.
inkwell-memory CLAUDE.md
Instructions for veronchenko/inkwell-memory, covering claude.md — inkwellmemory, layout, multi-tenant mode (inkwellmultitenant=1), conventions and testing.
memory-mcp-1file AGENTS.md
Instructions for pomazanbohdan/memory-mcp-1file, covering ⛔ l0 invariants (never violate under any circumstance), detection heuristic, 🔀 phase transition routing (⛔ blocking), gate-0: phase identification & loading and 🧾 proof-of-load requirement (critical).