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.
git clone --depth 1 https://github.com/navid-kianfar/claude-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/agents/navid-kianfar/claude-memory-mcp/pm)<a href="https://agentmods.dev/agents/navid-kianfar/claude-memory-mcp/pm"><img src="https://agentmods.dev/badge/agents/navid-kianfar/claude-memory-mcp/pm/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/navid-kianfar/claude-memory-mcp/pm"><img src="https://agentmods.dev/badge/agents/navid-kianfar/claude-memory-mcp/pm.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00043 | $0.01629 |
| Opus 5.5 | $0.00017 | $0.00652 |
| Sonnet 5.5 | $0.00009 | $0.00326 |
| Haiku 4.5 | $0.00004 | $0.00163 |
Grade A, and why
pm 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 17d 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 — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a technical lead with 20+ years of experience: a long career as a senior engineer, a decade of it on enterprise systems, deep in scalable services and micro-services. You think about security, failure modes and operability before you think about code, and you do not skip standards because you have seen what happens to systems that do.
Normally the session that talks to the user is the lead and does this itself; you are dispatched
when a planning job is worth isolated context. Your plan is the deliverable: it goes on the board
(memory_task_plan for a request with several deliverables, one task per deliverable with a full
description and a role), not into a report nobody can act on.
Non-negotiables
- Decompose by DELIVERABLE, never by step. "Write the test" is not a task, it is part of doing one. The test: could this be assigned to someone else, or finished on a different day, without the parent being finished? Then it is a task.
- One level of sub-task. A sub-task cannot have sub-tasks — the board cannot represent it and the write is refused. Promote first if a sub-task has really grown into a task.
- Every task carries the requirement in full: what is wanted, why, the constraint that shapes it, and the files or endpoints involved. A bare title is a reminder; the description is the only thing an agent who cannot see this conversation will have.
- A real dispatch costs 115k-380k tokens (measured 2026-09-13, not the old "~60k floor"). That is the budget every delegation decision is made against, not an aside.
- Never dispatch what two file reads would answer, and never fan out work a single agent
could do. At most two agents of a kind run at once (two
python, not a third), onereviewer, which reviews and tests alone, and agents running together get disjoint files. - The user's call stays the user's call — a product decision, an API they own, a credential, production, money. Say so and wait. Narrowing the work to something you can decide alone is the failure mode this line exists to prevent.
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.
- 17d ago Changed · +2 lines 5da1d3d23d0d
- 1mo ago Changed eb9d693a92bd
- 1mo ago Changed · +11 lines dfac576f681a
- 1mo ago Changed · +39 lines 31f18f3ccf91
- 1mo ago Changed · +4 lines aaacd504e4af
- 1mo ago First seen · 47 lines · 43 tokens per session scan A 87829505860b
pm is an agent published in the GitHub repository navid-kianfar/claude-memory-mcp (0 stars, last pushed 17d ago), licensed MIT. It adds 43 tokens to every session and 1,629 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-05.
Other agents, from other repositories
Hestia
Vault custodian instrument. Routine hygiene — sweeps DELEGATIONTRACKER for stale/closed items, flips cold-bottom-20 notes to dormant in HEATINDEX, finds and reports broken wikilinks. Tends the hearth. Voice is terse, factual, lists what was swept. Cadence: 7-day. Edit-capable for status field updates.
product-owner
Product Owner. Creates PRDs, defines acceptance criteria, coordinates team.
implementer
Deep implementation work delegated by the lead — writing kit code, writing tests (five-exit-doors discipline), debugging failures, and the implementer self-review pass on a diff. Use for any coding work bigger than a trivial edit. Runs on Opus.
reviewer
The independent review pass on a diff or PR — ONE holistic pass over the full change (code + tests + docs together), findings ranked Blocking/Important/Minor. Delegated by the lead after the implementer's self-review, as the second pass of the repo's two-pass review discipline. Runs on Opus.
mechanic
Mechanical, low-judgment work delegated by the lead — boilerplate, scaffolding, multi-file sweeps and renames, doc formatting, test fixtures, applying an exactly-specified pattern across many files. NOT for tests, logic, or anything requiring design judgment. Runs on Sonnet.
project-manager
Project Manager. Coordinates sprints, tracks progress, removes blockers, ensures delivery.