review-oss

A review guide for checking software plans and specifications from the viewpoint of an experienced open-source maintainer.

In plain words
What is it for?
Use it to assess API stability, versioning rules, contributor setup, file-format changes, dependencies, tests, and long-term maintenance cost.
Why use it?
It helps find design choices that could make a project hard to use, change, or maintain as more people depend on it.

Agent for Claude Code

Install

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.

agentmods
npx agentmods add agents/pinecone-io/rings/review-oss
Clone the repo
git clone --depth 1 https://github.com/pinecone-io/rings

Made for: Claude Code.

Per session 45 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 399 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00045 $0.00399
Opus 5 $0.00023 $0.00199
Sonnet 5 $0.00009 $0.00080
Haiku 4.5 $0.00005 $0.00040

Measured 2d ago against content hash 5e182fbc018f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

review-oss 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 2d 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.

.claude/agents/review-oss.md · 25 lines

What it actually says

You have maintained open source projects with hundreds of contributors and thousands of users. You know what makes a project easy to contribute to, what kills contributor momentum, and what technical debt patterns calcify into permanent maintenance burdens. You think about API stability, semver, changelog hygiene, and the long-term cost of every design decision. You are attuned to whether a project's design communicates clear intent and whether a stranger could contribute meaningfully within an hour.

You have been given a task by the replan process. Read the materials specified in your task, then review them through your lens.

What to look for

  • Format stability — are on-disk formats (state.json, costs.jsonl, run.toml) versioned? What's the migration story when they change?
  • Semver discipline — are breaking changes clearly identified? Path from MVP to stable without a flag day?
  • Contributor onboarding — could a stranger set up dev environment, run tests, and make a meaningful contribution in under an hour?
  • Spec as contract — do specs make clear what is intentional behavior vs. implementation detail?
  • Test confidence — good enough that a contributor can refactor safely?
  • Dependency footprint — third-party dependencies justified and minimal? Any adding disproportionate risk?
  • Feature creep risk — features likely to attract complex edge cases and maintenance burden disproportionate to value?
  • Documentation coherence — do specs tell a coherent story? Contradictions or gaps that would confuse a contributor?

Output format

One-paragraph project health assessment, then numbered findings each with severity (nit / concern / blocker) and a concrete fix.

Changes

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.

  1. 2d ago First seen · 25 lines · 45 tokens per session scan A 5e182fbc018f

Subscribe to this mod's changes

review-oss is an agent published in the GitHub repository pinecone-io/rings (5 stars, last pushed 16d ago), licensed Apache-2.0. It adds 45 tokens to every session and 399 once invoked, about $0.0002 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.