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/formonkey/knowledge-memory-mcp/agents-mdgit clone --depth 1 https://github.com/formonkey/knowledge-memory-mcpWhat 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 | $0.01240 | $0.01240 |
| Opus 5 | $0.00620 | $0.00620 |
| Sonnet 5 | $0.00248 | $0.00248 |
| Haiku 4.5 | $0.00124 | $0.00124 |
Grade A, and why
knowledge-memory-mcp 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 yesterday.
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 — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Instructions
Purpose Of This File
AGENTS.md is guidance for Codex agents working inside this repository. It is not part of the MCP runtime and is not required by users who only consume the MCP through npx.
Its job is to tell agents how to use the knowledge_memory MCP consistently while editing, reviewing, or maintaining this repository.
Objective
This workspace uses the knowledge_memory MCP to remember corrections, criteria, and recurring mistakes across conversations. Any agent that implements, reviews, or fixes work should consult and apply those criteria when they are still relevant.
Shared Stores
Persistent memory lives in plain Markdown files:
~/.codex/changes.md: cross-project criteria.<project>/.codex/changes.md: project-specific criteria.
Agents must not edit those files manually. Interaction must go through the knowledge_memory MCP.
Mandatory knowledge_memory Usage
Available tools:
add_local: save a project-specific memory entry.add_global: save a cross-project memory entry.list_change_index: read the compact low-token index.list_tag_catalog: read the recommended tags for saved entries.list_changes: read full entries from project + global memory.get_change: read one exact entry by id.search_changes: search entries by text, tags, or paths.get_relevant_changes: retrieve entries relevant to a task summary.
Before implementing, reviewing, or fixing code:
- Call
list_change_indexfirst to inspect the compact index without spending many tokens. - Use tags from the index to decide which entries to retrieve.
- Then call
get_change,search_changes, orget_relevant_changesonly for entries that look relevant to the task. - If you need to find a preference, recurring mistake, path, or specific concept, use
search_changes. - If you already know the exact change id, use
get_change. - When working with several projects in one conversation, pass
projectPathto select the right project memory.
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.
- yesterday First seen · 127 lines · 1,240 tokens per session scan A 73db1f4e29f5
knowledge-memory-mcp AGENTS.md is an instructions file published in the GitHub repository formonkey/knowledge-memory-mcp (0 stars, last pushed 21d ago), licensed MIT. It adds 1,240 tokens to every session, about $0.0062 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
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.
vscode buildNext.instructions.md
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
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
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.