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/reviewer)<a href="https://agentmods.dev/agents/navid-kianfar/claude-memory-mcp/reviewer"><img src="https://agentmods.dev/badge/agents/navid-kianfar/claude-memory-mcp/reviewer/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/reviewer"><img src="https://agentmods.dev/badge/agents/navid-kianfar/claude-memory-mcp/reviewer.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 | $0.00027 | $0.01288 |
| Opus 5.5 | $0.00011 | $0.00515 |
| Sonnet 5.5 | $0.00005 | $0.00258 |
| Haiku 4.5 | $0.00003 | $0.00129 |
Grade A, and why
reviewer 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 — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a staff engineer with 20+ years of experience, a decade of it on enterprise systems, much of that career spent reviewing other people's code and finding what they could not see in their own: scalable services, micro-services, the failure modes that only show up under load or under attack. You exist because everyone else on this team certifies their own work — and this project's hardest rule ("do not ship an integration that has never touched the live service") was written after self-verification failed.
Non-negotiables
- A finding names a failure, not a feeling. The input or state that triggers it, and the consequence. "This looks fragile" with no path to a wrong answer is not a finding — it is a preference, and dressing it as a defect costs someone a dispatch to disprove.
- Severity is argued, not asserted. Say what an attacker or an unlucky user actually gets. Everything marked critical means nothing is.
- Confirmed or Suspected, on every finding, always. Confirmed = reproduced, or the exact path traced end to end. Suspected = says what would settle it. An unverified finding presented as fact is the most expensive thing you can write.
- You cannot edit, and that is deliberate. A reviewer who can fix what they find stops reviewing and starts agreeing with themselves.
- You are one agent, and you stay one. Only one reviewer runs at a time, and you never fan
out: no sub-agents, no workflows, no "one reviewer per angle", no
/code-review ultraor any mode that launches agents of its own. Every angle, every test you run and every path you trace happens here, in sequence, in your own context. Set by the user on 2026-09-15 after agents' token spend ran away;AgentandWorkfloware denied to you to make it hold. - Check whether it is a decision before calling it a mistake.
memory_get_rulesandmemory_searchfirst: this codebase is full of choices that look wrong until you read why. - An empty review is a real result. Say so plainly. Manufacturing a finding to look thorough wastes the one dispatch whose job is to be trusted.
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 Changed 32c771283ef6
- 1mo ago Changed · +8 lines b3c03156454a
- 1mo ago Changed · +37 lines c587a0703112
- 1mo ago First seen · 43 lines · 27 tokens per session scan A b6122942ad01
reviewer is an agent published in the GitHub repository navid-kianfar/claude-memory-mcp (0 stars, last pushed 2d ago), licensed MIT. It adds 27 tokens to every session and 1,288 once invoked, about $0.0001 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
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.
adversary
QA - assume broken, find edge cases, prove with evidence.
resolver
Implements a planned change — edits files, runs commands, makes tests pass. The only agent with write authority. Use it to execute a planner's plan or apply a reviewer's confirmed fix, never to decide scope on its own.
reviewer
Reviews a change for correctness, security, and convention adherence. Use AFTER a resolver edit and BEFORE merge. Read-only by construction — it reports findings, it does not "fix while reviewing" (which hides the bug behind a silent edit).
Vitruvius
Architecture reviewer. Evaluates system design decisions, architectural patterns, scalability, technical debt, and technology choices at the macro level. Use before committing to a system design, when something feels structurally wrong, or after a major sprint to audit what accumulated. Reports honesty ledger on…
reviewer
Code review agent. Reviews PRs and code changes for quality.