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 agentmods add skills/apurvbazari/claude-plugins/render-reviewnpx skills add ApurvBazari/claude-plugins --skill render-reviewgit clone --depth 1 https://github.com/ApurvBazari/claude-pluginsWrote 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/apurvbazari/claude-plugins/render-review)<a href="https://agentmods.dev/skills/apurvbazari/claude-plugins/render-review"><img src="https://agentmods.dev/badge/skills/apurvbazari/claude-plugins/render-review.svg" alt="Measured on agentmods" 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 | $0.00085 | $0.01127 |
| Opus 5 | $0.00043 | $0.00563 |
| Sonnet 5 | $0.00017 | $0.00225 |
| Haiku 4.5 | $0.00009 | $0.00113 |
Grade A, and why
render-review 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 4d 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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Render Review — Pure HTML Render of a review-findings Object
You are invoked by an orchestrator (not a human). You take a review-findings object that has
ALREADY been computed (by lens:engine), render it to a self-contained interactive HTML review
document, and return the written path. You are stateless and write-once: the only file you create
is the caller's outputPath. You never write review-state.json, never create a task list, and never
re-run finders.
Your inputs (supplied in context by the caller)
findings— the currentreview-findingsobject (required).priorFindings— a prior-runreview-findingsobject (optional; enables reconcile).diffRef— a git ref/range to read for annotated diff hunks (optional).spec/plan/adherence— intent for the adherence matrix (optional).outputPath— the absolute path to write the HTML (required; create the dir if absent).findings.emptyScope— the discriminator for nothing to review (true means the caller's scope was empty; false/absent means an ordinary review). Full contract:../engine/references/engine-api.md.
Step 1: Reconcile (compute-only, in memory)
If findings.emptyScope is true, return noop: nothing to review and write NO artifact.
If priorFindings is supplied, reconcile findings against it per ../review/references/reconcile.md
§ Orchestrator mode — fingerprint by dimension + normalized claim + stable context, label each
finding fixed | still-open | new | possibly-resolved, and compute delta {fixed,new,stillOpen} +
severityTrend. Write NOTHING. If priorFindings is absent, skip — this is a clean first pass (no
iteration labels, no trend).
Step 2: Assemble the review-model
Build the review-model per ../review/references/review-model-assembly.md: narrative spine +
adherence (from the adherence block / requirements-dimension findings) + findings[] (each with
iteration, status, location, claim, detail, suggestedFix) + files[].risk + diffHunks[]
(read diffRef if supplied; omit the panel if unavailable) + derived verdict (from
recommendedEscalation). Apply omit-empty; never stub.
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.
- 4d ago First seen · 69 lines · 85 tokens per session scan A 8cddd7d4ec75
render-review is a skill published in the GitHub repository ApurvBazari/claude-plugins (0 stars, last pushed 28d ago), licensed MIT. It adds 85 tokens to every session and 1,127 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 skills, from other repositories
cross-platform
Cross-platform development patterns for macOS, Windows, and Linux.
shell-scripting
Shell scripting best practices for cross-platform CLI tools.
c-notify
Send native macOS notification center alerts from the command line using terminal-notifier.
notifications
Send notifications through the unified notification router.
telegram-setup
Connect a Telegram bot to the Vellum Assistant gateway with automated webhook registration and credential storage.
chat-complex-documents
Chat with and search your complex documents — ask questions, extract tables and fields, and get answers grounded in the source. Connects the hosted Unstructured Transform MCP server to parse, structure, and enrich PDFs, Word/Excel/PowerPoint, images, scanned files, emails, and 60+ other formats into clean, AI-ready…