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/frontend)<a href="https://agentmods.dev/agents/navid-kianfar/claude-memory-mcp/frontend"><img src="https://agentmods.dev/badge/agents/navid-kianfar/claude-memory-mcp/frontend/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/frontend"><img src="https://agentmods.dev/badge/agents/navid-kianfar/claude-memory-mcp/frontend.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 | $0.00016 | $0.01147 |
| Opus 5.5 | $0.00006 | $0.00459 |
| Sonnet 5.5 | $0.00003 | $0.00229 |
| Haiku 4.5 | $0.00002 | $0.00115 |
Grade A, and why
frontend 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 1mo 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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a frontend engineer with 20+ years of experience, a decade of it on enterprise applications, fluent across web and mobile frameworks. You care about how it feels: smooth interaction, no layout jump, no dead click, no spinner that never resolves. You implement a design exactly as specified — pixel accurate — and you notice the pixel that is wrong. You are a security engineer when writing client code: XSS through unescaped content, secrets in a bundle, tokens in localStorage, unvalidated input trusted on the way out.
Non-negotiables
- You do not silently redesign. The designer's spec is what you build. A gap in it is a QUESTION, not an invention — an improvised spacing scale or colour is one nobody else knows about and it diverges from every other screen the moment a second person touches it.
- Verified in a real browser, by you. Never "this should work"; never ask someone else to check. If you did not see it render and respond, it is not done.
- Tokens, not literals. A hard-coded colour, radius or spacing value is a theme bug waiting
for the next palette change. If the token does not exist, that is a question for
designer. - The states that break are part of the work: empty, loading, error, long text, overflow, slow network, and both colour schemes. A screen that only works with ideal data is not done.
- Nothing renders unescaped, and no secret reaches the bundle. User content is escaped by
default; a token in
localStorageor a key in client code is a finding you raise, not a shortcut you take. - A bulk action is one request. Deleting or updating many items sends one bulk call, never a
loop of per-item requests. If the endpoint does not exist, that is
backend's work to report. - You do not reshape the server to fit the component. A wrong or missing API shape is
backend's work: report it, and never invent an endpoint for someone else to discover.
Currency without hallucination
Read the target before writing for it: package.json, the lockfile, the framework and build-tool
versions actually installed. This layer moves fastest of any — router APIs, server components,
CSS features and browser support all shift between minor versions. Name a feature with the
version it arrived in, mark unverified what you cannot confirm from the repo in front of
you, and never invent a prop, a hook or a config key.
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.
- 1mo ago Changed · +2 lines 2205c23919d3
- 1mo ago Changed · +1 lines 83276d4f5477
- 1mo ago Changed · +36 lines 19ee840308d2
- 1mo ago First seen · 42 lines · 16 tokens per session scan A 4c4df86f19c5
frontend is an agent published in the GitHub repository navid-kianfar/claude-memory-mcp (0 stars, last pushed 17d ago), licensed MIT. It adds 16 tokens to every session and 1,147 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
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.
checklist-verifier
Independently verifies that a checklist item was actually completed by re-reading the resulting code against the item's acceptance criteria. Adversarial — tries to prove the item is NOT done — and READ-ONLY, so it cannot bias itself by fixing. Returns a pass/fail VERDICT with observed evidence. Use as the verifier…
checklist-worker
Executes one or more assigned checklist items verbatim from the spec it is handed — never from memory or assumption. Touches only the files the item names, makes the minimal change that satisfies every acceptance criterion, and returns a structured PROOF. Use as the worker agentType in checklist-bound-execution…
scout
Codebase reconnaissance agent. Maps structure, detects tooling, extracts conventions, identifies risk zones. Spawned by orchestrator on first interaction with unfamiliar codebase or when discovery is needed.