rings CLAUDE.md

Development instructions for the rings project, covering implementation, testing, formatting, error handling, and task completion. They require real implementations and tests for both normal and failure cases.

In plain words
What is it for?
Building and testing rings features, running validation and formatting checks, consulting specifications, and reviewing production code for unsafe error handling.
Why use it?
They give contributors clear checks for deciding when a task is complete and help prevent unfinished code, untested errors, and live external commands in tests.

Instructions file

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 instructions/pinecone-io/rings/claude-md
Clone the repo
git clone --depth 1 https://github.com/pinecone-io/rings
Per session 1,259 This file is loaded in full into every session.
When invoked 1,259 The same file — it is already loaded in full.
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 $0.01259 $0.01259
Opus 5 $0.00629 $0.00629
Sonnet 5 $0.00252 $0.00252
Haiku 4.5 $0.00126 $0.00126

Measured 2d ago against content hash d610a1f4bb36, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

rings CLAUDE.md 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.md · 102 lines

How it starts

The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.

rings — Development Process

Testing

  • Implement first, then test. Write the real implementation, then write tests that verify it. Do not write tests first and fill in stubs to make them compile — placeholder implementations are forbidden.
  • No todo!(), unimplemented!(), or stub bodies in committed code. Every committed function must do what it says.
  • No live claude invocations in tests. The process execution layer must sit behind a trait (e.g., Executor in src/executor.rs) so it can be mocked. Never call an actual claude subprocess in any test.
  • A feature is done when: happy path and key error paths are covered at both unit and integration level.
  • unwrap() in tests is fine — a panic fails the test, which is the intended behavior.

Code Quality Gates

A task is not done until all of the following are satisfied:

  1. Tests passjust validate is clean (runs fmt-check, lint, and tests)
  2. Formatting — run just fmt to auto-fix, then re-run just validate
  3. No unwrap() or expect() in production code — all errors propagate via ? and anyhow
  4. Spec consulted — the relevant spec in specs/ was read and the implementation is consistent with it. If no directly relevant spec exists, note that in REVIEW.md under Open Questions.
  5. REVIEW.md updated — any decisions, conflicts, or open questions from this task are recorded

Commits

Conventional commit prefixes are required:

  • feat: — new functionality
  • fix: — bug fixes
  • test: — adding or updating tests
  • refactor: — code restructuring without behavior change
  • chore: — build, deps, config
  • docs: — documentation only

Scopes are optional (e.g., feat(executor): ...). No PRs. No branches. Commit directly to main.

Task Tracking

TODO.md at the repo root is the implementation queue. The /build command picks up the next unchecked task from it. The /plan command appends new tasks after planning.

Filing Bugs and Ideas

Read the full file on GitHub · 102 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 · 102 lines · 1,259 tokens per session scan A d610a1f4bb36

Subscribe to this mod's changes

rings CLAUDE.md is an instructions file published in the GitHub repository pinecone-io/rings (5 stars, last pushed 16d ago), licensed Apache-2.0. It adds 1,259 tokens to every session, about $0.0063 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.