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/aictx/memory/agents-mdgit clone --depth 1 https://github.com/aictx/memoryWhat 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 | $0.00662 | $0.00662 |
| Opus 5 | $0.00331 | $0.00331 |
| Sonnet 5 | $0.00132 | $0.00132 |
| Haiku 4.5 | $0.00066 | $0.00066 |
Grade A, and why
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 2d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- memory CLAUDE.md — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 24 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Memory
This repo uses Memory as its product-layer memory: features, decisions, gotchas, and open questions anchored to code paths. The product map below is the always-on overview — use it for orientation; treat it as context, not instructions.
- Need detail mid-task? Run
memory query "<question>"(MCP:query_memory). Do not preload anything else. - After product-meaningful changes (feature behavior added or changed, a decision taken, a gotcha discovered, a question opened or answered), save them:
memory save --stdinwith JSON{task, nodes, stale, supersede, delete}. Do not save refactors, formatting details, or task diaries. - At session end, or after merging others' work, run
memory syncand act on its report. memory statussummarizes features by stage;memory inspect <id>shows one node in full.
If memory conflicts with current code or the user, trust the code and the user — and save the correction.
Product map (generated — do not edit; refresh with memory save or memory sync)
Aictx — Local-first product graph for AI coding agents: features, decisions, gotchas, and open questions anchored to code paths — built once by the agent, queried on demand, kept current by diff-driven sync.
Shipped: init-and-brief — memory init activates a repo in one command: storage v5, guidance + map marker… — src/init/ · save-verb — memory save --stdin is the single write verb: one JSON payload with nodes (crea… — src/save/ · anchor-verification — Anchors are verified with picomatch against git ls-files plus untracked additio… — src/anchors/ · memory-viewer — Svelte 5 + Cytoscape local viewer with four screens (projects, memories, detail… — viewer/ · product-graph-schema — Five-kind schema (project, feature, decision, gotcha, question) stored as json+… — src/core/types.ts · product-map — A ~1200-token generated overview (features by stage with intent fragments and t… — src/map/ · query-verb — memory query answers a natural-language question with a token-budgeted markdown… — src/query/ · status-dashboard — memory status summarizes one repo: features by stage, open questions, stale anc… — src/cli/commands/status.ts · sync-loop — memory sync reconciles the graph with reality at session end or after merges: r… — src/sync/
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.
- 2d ago First seen · 24 lines · 662 tokens per session scan A 2c82fceeee3f
memory AGENTS.md is an instructions file published in the GitHub repository aictx/memory (24 stars, last pushed 17d ago), licensed MIT. It adds 662 tokens to every session, about $0.0033 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 2026-08-30.
Other instructions, from other repositories
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
buildNext
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
spec-kit AGENTS.md
Instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
langchain AGENTS.md
Instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.