process-ideas

A workflow for turning rough notes in queues/IDEAS.md into reviewed feature proposals or new project entries. It compares ideas with the project’s existing specifications and asks several review roles to examine them.

In plain words
What is it for?
Use it to classify ideas as already covered, extensions, new features, or out of scope, then produce concrete proposals for the ideas that remain.
Why use it?
It prevents ideas from being developed without checking whether they already exist, extend an existing feature, conflict with project principles, or need a different scope.

Command 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 commands/pinecone-io/rings/process-ideas
Clone the repo
git clone --depth 1 https://github.com/pinecone-io/rings

Made for: Claude Code.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 926 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 $0.00000 $0.00926
Opus 5 $0.00000 $0.00463
Sonnet 5 $0.00000 $0.00185
Haiku 4.5 $0.00000 $0.00093

Measured 2d ago against content hash 9676a57a42e6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

process-ideas 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/commands/process-ideas.md · 82 lines

How it starts

The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Read rough ideas from queues/IDEAS.md, evaluate them against the existing specs, run them through the full review panel in parallel, then produce concrete spec proposals or new feature entries.

Steps

1. Load context

  • If queues/IDEAS.md does not exist at the project root, tell the user to create one with their rough notes and stop.
  • Read queues/IDEAS.md in full.
  • Read specs/feature_inventory.md to understand what is already specified.
  • Read specs/index.md and any spec files directly relevant to the ideas.
  • Read specs/overview.md and specs/mvp.md to understand design principles and scope.

2. Classify each idea

For each idea in queues/IDEAS.md, classify it as:

  • Already covered — essentially described by an existing spec; note the F-NNN number(s) and explain how.
  • Extension — adds nuance or a new option to an existing feature; identify the F-NNN being extended.
  • New feature — genuinely not covered; note which spec file it would belong in.
  • Out of scope / conflict — conflicts with a design principle; explain why and suggest an alternative if one exists.

Set aside anything classified as "already covered" or "out of scope" — do not send those to the review panel.

3. Dispatch review panel in parallel

For all ideas classified as extension or new feature, launch ALL of the following agents simultaneously using the Agent tool. Give each the same task:


"You are a member of the rings project review panel. Before reviewing, orient yourself by reading:

  • specs/index.md — what rings is and core concepts
  • specs/overview.md — design principles and target user
  • specs/mvp.md — what was built first and why
  • specs/feature_inventory.md — what is already specified

Review the following proposed ideas and provide your perspective from your area of expertise. For each idea, identify concerns, risks, gaps, or improvements before we commit to writing them into the spec. Also note anything the idea is missing that your area of expertise would require.

Read the full file on GitHub · 82 lines

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 · 82 lines · 0 tokens per session scan A 9676a57a42e6

Subscribe to this mod's changes

process-ideas is a command published in the GitHub repository pinecone-io/rings (5 stars, last pushed 16d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 926 tokens. 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.