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/joshdougall/memory-mcp/agents-mdgit clone --depth 1 https://github.com/joshdougall/memory-mcpWrote 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/joshdougall/memory-mcp/agents-md)<a href="https://agentmods.dev/instructions/joshdougall/memory-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/joshdougall/memory-mcp/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 | $0.01040 | $0.01040 |
| Opus 5 | $0.00520 | $0.00520 |
| Sonnet 5 | $0.00208 | $0.00208 |
| Haiku 4.5 | $0.00104 | $0.00104 |
Grade A, and why
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 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.
How it starts
The opening of the file, as written. The whole thing — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Memory Instructions
A persistent memory MCP server is running and available to you. Use it to store and retrieve knowledge that should survive across sessions — decisions, patterns, references, and feedback that would otherwise be lost when the conversation ends.
Connection
- Endpoint:
http://127.0.0.1:3106/mcp(MCP over HTTP, Streamable HTTP transport) - Auth: If
MEMORY_MCP_AUTH_TOKENwas set, includeAuthorization: Bearer <token>in requests. Check with the user if unsure.
When to read
At the start of each session, search for memories relevant to the current project or task before asking the user to re-explain context:
memory_search(tags=["your-project-name"])
When to write
Write when you discover something that should be remembered across sessions:
- A pattern or convention the user corrected you on
- An architectural decision and its rationale
- A reference to an external resource or tool
- A recurring preference or feedback
- A project-level fact (deadline, constraint, stakeholder)
Do not write:
- Ephemeral task state (use a STATE.md file for that)
- Code patterns obvious from reading the repo
- Anything already documented in project files
Memory types
| Type | Use for |
|---|---|
pattern |
Recurring conventions, idioms, or approaches |
decision |
Architectural or technical choices with rationale |
reference |
Pointers to external resources, docs, or tools |
feedback |
How the user wants you to behave or approach work |
incident |
Post-mortems and lessons from failures |
project |
Project-level facts (team, deadlines, constraints) |
entity |
Named things (people, systems, accounts) |
state |
Short-lived state that spans a few sessions |
Available tools
| Tool | Description |
|---|---|
memory_search |
Filter by tags (intersection), type, project, or text |
memory_get |
Fetch one entry by ID — increments hit counter |
memory_set |
Create or update an entry — versioned on every write, optional compare-and-set |
memory_list |
List entries with optional type/project filter |
memory_delete |
Delete an entry (tombstone version written first) |
memory_history |
View version history for an entry |
memory_rollback |
Restore an entry to a previous version |
memory_prune_candidates |
Surface zero-hit stale entries for review (read-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.
- 3d ago First seen · 112 lines · 1,040 tokens per session scan A 64388830a9d7
memory-mcp AGENTS.md is an instructions file published in the GitHub repository joshdougall/memory-mcp (2 stars, last pushed 17d ago), licensed MIT. It adds 1,040 tokens to every session, about $0.0052 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
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
Instructions for aeonfun/aeon, covering aeon, how aeon works, strategy, voice and soul file hierarchy (read in this order).
inkwell-memory CLAUDE.md
Instructions for veronchenko/inkwell-memory, covering claude.md — inkwellmemory, layout, multi-tenant mode (inkwellmultitenant=1), conventions and testing.
RNR-Enhanced-Cognee AGENTS.md
AGENTS.md instructions for vincentspereira/RNR-Enhanced-Cognee, covering rnr enhanced cognee implementation for codex, critical requirements, 1. ascii-only output (no unicode encoding), 2. dynamic categories (no hardcoded categories) and 3. standard memory mcp interface.
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).
openexp CLAUDE.md
Instructions for anthroos/openexp, covering openexp — development instructions, memory protocol (mandatory), before starting any task, after completing a task and when the user shares context.