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/corbym/memoryweb/agents-mdgit clone --depth 1 https://github.com/corbym/memorywebWhat 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 | $0.03153 | $0.03153 |
| Opus 5 | $0.01577 | $0.01577 |
| Sonnet 5 | $0.00631 | $0.00631 |
| Haiku 4.5 | $0.00315 | $0.00315 |
Grade A, and why
memoryweb 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.
How it starts
The opening of the file, as written. The whole thing — 297 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — guidance for AI agents using memoryweb
This file is for agents connected to memoryweb via MCP. It tells you how to use the tools correctly, what the tools will and won't surface, and how to behave around archiving, drift, and knowledge gaps.
What memoryweb is
A persistent knowledge graph for a project or set of projects. You file concepts and decisions as nodes, connect them with typed narrative edges, and retrieve them by searching or following connections.
It is called memoryweb. Nothing else.
Core tool guide
Orientation at session start
Always call orient for the relevant domain before answering questions about a
project. Do not rely on your context window or training for project state.
orient returns all live nodes for the domain, recent activity, and a
declared_spine — the curated history of key decisions in chronological order.
Weigh the spine heavily when synthesising.
If you do not know what domains exist, call domains first.
Filing knowledge
remember— file a concept, decision, or finding. Acceptsrelated_toto auto-connect at creation. Returnssuggested_connectionsandpossible_duplicates— act on these before filing more nodes. Supply anitemsarray to file multiple nodes in one transaction.revise— updatelabel,description,why_matters,tags, oroccurred_aton a live node without archiving it. Supply anitemsarray for batch updates. Writes an audit log entry on every call. When updating a decision, do not paste new source material into its description — file anode_kind=findingfor the evidence and connect withdepends_onorcaused_by.
Before filing a node: search first. Infer the domain from search results;
prefer an existing domain over creating a new one. Creating a new domain hides
the memory from every other domain's orient and domain-scoped search —
only create one when no existing domain covers the topic. If a similar node
exists, suggest linking with connect rather than creating a duplicate.
Unfiled duplicates are the primary cause of orphan nodes and audit drift.
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 · 297 lines · 3,153 tokens per session scan A e149ed5a7945
memoryweb AGENTS.md is an instructions file published in the GitHub repository corbym/memoryweb (12 stars, last pushed 3d ago), licensed MIT. It adds 3,153 tokens to every session, about $0.0158 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.