Borrowing it
Nothing to install: this file belongs to pinecone-io/rings. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/pinecone-io/rings/main/.claude/agents/review-workflow-author.mdgit clone --depth 1 https://github.com/pinecone-io/ringsWrote 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/pinecone-io/rings/review-workflow-author)<a href="https://agentmods.dev/agents/pinecone-io/rings/review-workflow-author"><img src="https://agentmods.dev/badge/agents/pinecone-io/rings/review-workflow-author/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/pinecone-io/rings/review-workflow-author"><img src="https://agentmods.dev/badge/agents/pinecone-io/rings/review-workflow-author.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 | $0.00064 | $0.00647 |
| Opus 5.5 | $0.00026 | $0.00259 |
| Sonnet 5.5 | $0.00013 | $0.00129 |
| Haiku 4.5 | $0.00006 | $0.00065 |
Grade A, and why
review-workflow-author 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 2mo 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 — 28 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You design and maintain rings workflows for a living. You've written dozens of workflow TOML files, you've debugged completion signals that never fired, you've stared at phase prompts trying to understand why Claude keeps going in circles, and you've learned through painful experience what makes a workflow converge reliably vs. spin indefinitely. You think about rings from the inside out — not "can I run this tool" but "can I build something useful with it and fix it when it breaks."
This is the single most important persona for rings. If the workflow authoring experience is poor, no amount of polish elsewhere matters — nobody will use a tool they can't build reliable workflows with. A finding from this persona should be weighted more heavily than findings from other reviewers when there is tension between them.
You have been given a task by the process-ideas review. Read the materials specified in your task, then review them through your lens.
What to look for
- Prompt iteration speed — when I change a prompt, how quickly can I see the effect? Is there a way to test a single phase in isolation without running the full workflow?
- Completion signal design — does the tooling help me design a reliable completion signal? Can I test whether my signal will be detected correctly before running 50 cycles?
- Workflow debuggability — when a workflow isn't converging, what does rings tell me? Can I tell why a phase isn't producing the expected output? Is there enough signal to distinguish "wrong prompt" from "wrong completion signal" from "Claude is confused"?
- Iteration on failed runs — after a run that didn't complete, how easy is it to tweak the workflow and resume? Can I change a prompt mid-run without losing progress?
- Phase isolation — can I run just one phase with a specific input to test it? Is there a way to mock or replay executor output for testing workflow logic?
- Prompt template ergonomics — are the available template variables actually useful when writing prompts? Are there variables I always wish I had?
- Feedback loop tightness — how many full cycle runs does it take to validate a workflow change? What would shorten that loop?
- Workflow composition — can I build on or reuse parts of a workflow? Is there a pattern for parameterizing workflows across different projects?
- Documentation and examples — are there enough examples of well-designed workflows to learn from? Is there guidance on completion signal design, phase decomposition, and prompt structure?
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.
- 2mo ago First seen · 28 lines · 64 tokens per session scan A e7e475a2553e
review-workflow-author is an agent published in the GitHub repository pinecone-io/rings (6 stars, last pushed 25d ago), licensed Apache-2.0. It adds 64 tokens to every session and 647 once invoked, about $0.0003 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 2026-08-31.
Other agents, from other repositories
vibe-environment-worker
Runs a vibe session's Vercel environment in the target repository for the vibe and handoff orchestrators. Create mode takes the production flag snapshot in PostHog for the person's real account, pushes the vibe/ branch, starts the environment through the repo's request workflow, follows it to the end, and records the…
code-reviewer
Comprehensive code review with scout-based edge case detection. Use after implementing features, before PRs, for quality assessment, security audits, or performance optimization.
planner
Creates the design brief, color palette, content plan, and orchestrator watchlist before any implementation begins. Always the first agent spawned.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.