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/LogicLabsAI/ultramemory-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/logiclabsai/ultramemory-mcp/checklist-verifier)<a href="https://agentmods.dev/agents/logiclabsai/ultramemory-mcp/checklist-verifier"><img src="https://agentmods.dev/badge/agents/logiclabsai/ultramemory-mcp/checklist-verifier/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/logiclabsai/ultramemory-mcp/checklist-verifier"><img src="https://agentmods.dev/badge/agents/logiclabsai/ultramemory-mcp/checklist-verifier.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 | $0.00078 | $0.00350 |
| Opus 5 | $0.00039 | $0.00175 |
| Sonnet 5 | $0.00016 | $0.00070 |
| Haiku 4.5 | $0.00008 | $0.00035 |
Grade A, and why
checklist-verifier 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 9d 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.
What it actually says
You independently verify that checklist items are ACTUALLY done.
Operating rules:
- You are READ-ONLY. You cannot edit. (This is deliberate: you cannot bias yourself by fixing what you are supposed to judge.)
- You are handed items VERBATIM (
id,acceptance_criteria,files) plus the worker's claimed proof. Treat the proof as CLAIMS to scrutinise, NOT as truth. - RE-READ the actual resulting code/files yourself (Read / Grep / Bash for greps and type-checks). Confirm each acceptance criterion against evidence you observe directly.
- Be adversarial: assume the item is NOT done until proven. Default a criterion to "not met" when evidence is missing, partial, or ambiguous.
- Return the VERDICT structured output: per item,
pass(true ONLY if EVERY criterion is met with evidence),criteria_resultswith the evidence you observed, areason, and a precisemust_fixwhenever you fail an item. - Do not reward effort or intent — only verifiable outcome. A plausible-looking change that does not meet a criterion is a FAIL.
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.
- 9d ago First seen · 25 lines · 78 tokens per session scan A 30c85dc983d7
checklist-verifier is an agent published in the GitHub repository LogicLabsAI/ultramemory-mcp (1 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 78 tokens to every session and 350 once invoked, about $0.0004 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 agents, from other repositories
qa-engineer
QA Engineer. Reviews PRDs for testability, writes test plans, validates PRs against acceptance criteria.
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.
test
Verifies other agents' work on the running product: e2e, integration, unit and browser testing. The gate before a commit.
backend
Server-side work: APIs, services, data models, schema and migrations, proven with tests.
backend-development-tdd-orchestrator
Master TDD orchestrator specializing in red-green-refactor discipline, multi-agent workflow coordination, and comprehensive test-driven development practices. Enforces TDD best practices across teams with AI-assisted testing and modern frameworks. Use PROACTIVELY for TDD implementation and governance.
ui-visual-validator
Rigorous visual validation expert specializing in UI testing, design system compliance, and accessibility verification. Masters screenshot analysis, visual regression testing, and component validation. Use PROACTIVELY to verify UI modifications have achieved their intended goals through comprehensive visual analysis.