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 skills add flonat/flonat-research --skill review-clustergit clone --depth 1 https://github.com/flonat/flonat-researchWrote 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/skills/flonat/flonat-research/review-cluster)<a href="https://agentmods.dev/skills/flonat/flonat-research/review-cluster"><img src="https://agentmods.dev/badge/skills/flonat/flonat-research/review-cluster/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/skills/flonat/flonat-research/review-cluster"><img src="https://agentmods.dev/badge/skills/flonat/flonat-research/review-cluster.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00165 | $0.04720 |
| Opus 5 | $0.00082 | $0.02360 |
| Sonnet 5 | $0.00033 | $0.00944 |
| Haiku 4.5 | $0.00016 | $0.00472 |
Grade A, and why
review-cluster 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 8d 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 — 259 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review Cluster — Mid-Draft Adversarial Feedback
Parallel fan-out of a 4-agent read-only core on an active-drafting paper, optionally adding clarity-reviewer as a fifth agent, with auto-synthesise downstream. Lighter than
pre-submission-report --parallel; designed for tight iteration, not final-gate verification. Outputsreviews/<scope>/review-cluster/YYYY-MM-DD-cluster-report.md(scope = paper slug from the paper path).
Output Path
Per rules/review-artefact-routing.md (auto-loads in research projects (path-scoped to paper-*/ and paper/)):
- Source slug:
review-cluster - Write reports to:
reviews/<scope>/review-cluster/YYYY-MM-DD.md(scope = paper slug) inside the project. Path is relative to the research project root, not the Task-Management repo. - Never at project root (
./CRITIC-REPORT.md-style filenames are forbidden — pre-rule layout). - Idempotency: if today's file exists, append a same-day descriptor (
{date}-revision.md,{date}-r2.md,{date}-pre-submission.md) — never overwrite. - Index policy: the consolidated cluster report is an output-only artefact and receives no
Check=review-clusterrow. Each active reviewer receives its own row withTrigger=review-cluster. - Infrastructure repos (Task-Management, atlas-workspace, etc.): this section does not apply — the path-scoped rule won't load there.
Hard Rules
Existential — block output
- All active sub-agents are read-only. No git, no latexmk, no edits. See
subagent-write-guard.md. - Auto-synthesise via
synthesise-reviews(unless--no-synthesise). Mid-draft work needs an actionable revision plan, not 4 raw reports. - Skip if paper isn't compile-ready — run
latexfirst; review on broken builds is misleading. The skill checks compile-status before dispatching. - Cluster is for the user's own papers. For external papers, use
peer-revieweragent instead. - Prepare one common review input. After compile preflight, invoke
review-packetinfresh-reviewmode unless the user explicitly supplies a verified packet or requests--no-freeze-input. Record the packet archive hash and canonical PDF hash in every reviewer prompt and in the consolidated report. Packet creation itself creates noreviews/INDEX.mdverdict row.
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.
- 8d ago First seen · 259 lines · 165 tokens per session scan A 4fe390ec1cf2
review-cluster is a skill published in the GitHub repository flonat/flonat-research (133 stars, last pushed 16d ago), licensed MIT. It adds 165 tokens to every session and 4,720 once invoked, about $0.0008 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 2026-09-03.
Other skills, from other repositories
fin-paper-convert
Compile LaTeX to PDF and convert to target journal format.
fin-paper-plan
Generate structured paper outline adapted to target journal.
doc-audit
Evaluate one project document in detail — a workbook section, big picture, strategy map, handoff message, paper, brief, or primer — without editing it. Runs the mechanical lint, builds a claim ledger, types every headline against the eight claim statuses in CLAUDE.md, traces cited evidence to the scripts and logs that…
latex-compile
Compile a LaTeX document and fix every error plus aesthetic issue (overfull/underfull boxes, widows, alignment, fonts) for a clean PDF and log. Use this instead of running pdflatex/latexmk manually — it avoids the latexmk stale-log trap and silent grep failures on binary log output, and it reformats rather than…
claim-audit
Audit what a passing script actually established, before writing any prose about it — build the computed-object ledger, rewrite every check's label as the weakest statement that makes its body pass, and separate the verdict on someone else's work from your own new claim. Run after the script passes and BEFORE the…
nb-to-wolfbook
Convert Mathematica .nb or .m files to Wolfbook .wb format so they open and run in VS Code. Use when bringing existing .nb/.m files into Wolfbook, or to make an existing .wb bridge-safe.