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 commands/pinecone-io/rings/plangit clone --depth 1 https://github.com/pinecone-io/ringsWhat 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 | $0.00000 | $0.00982 |
| Opus 5 | $0.00000 | $0.00491 |
| Sonnet 5 | $0.00000 | $0.00196 |
| Haiku 4.5 | $0.00000 | $0.00098 |
Grade A, and why
plan 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 yesterday.
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 — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Draft and review an implementation plan for the next batch of prioritized features, then write it to TODO.md.
Steps
1. Select the batch
Read specs/feature_inventory.md. Select the next 5–10 features that have status PRIORITIZED.
Use these grouping criteria:
- Priority order — lower feature numbers first (generally)
- Logical grouping — prefer features sharing a spec file or implementation surface
- Coherent scope — the batch should be reviewable and implementable together
For each selected feature, read its spec file in full. Show the user the proposed batch and wait for approval before continuing.
2. Draft the plan
Using the Agent tool, launch the following 3 agents in parallel (single message, 3 tool calls):
Agents: impl-rust, impl-architecture, impl-deps
Prompt each with:
"You are a member of the rings initial planning panel. Orient yourself:
- Read
specs/index.mdandspecs/overview.mdto understand what rings is- Read the relevant source files in
src/that relate to your area of expertise- Read the spec files listed below for the selected features
These features are selected for the next implementation batch. Produce an initial technical plan from your area of expertise. For each feature, identify: source files to create or modify, key types/traits/structs to introduce, test cases required (unit and integration), and any cross-feature dependencies.
Selected features and their specs: [list F-NNN · Name · spec file for each]
Return your findings as structured markdown."
3. Review the draft
Using the Agent tool, launch the following 7 agents in parallel (single message, 7 tool calls):
Agents: impl-testing, impl-error-handling, impl-cli-framework, impl-serialization, impl-process-mgmt, impl-filesystem, impl-agent-ux
Prompt each with:
"You are a member of the rings implementation review panel. Orient yourself:
- Read
specs/index.mdandspecs/overview.mdto understand what rings is- Read the relevant source files in
src/that relate to your area of expertise- Read the spec files listed below for the selected features
The following features are selected for the next implementation batch. A draft technical plan has already been produced. Do a full implementation review from your area of expertise. For each feature, identify:
- Prerequisite work — missing abstractions, dependencies, or data model changes that must come first
- Design decisions — explicit choices with meaningful tradeoffs; include a recommended default
- Test cases — specific cases that must be covered
- Spec gaps — ambiguities that would affect implementation
Selected features and their specs: [list F-NNN · Name · spec file for each]
Draft plan: [full merged draft from Step 2]
Return numbered findings grouped by the four categories above. Skip categories with no findings."
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.
- yesterday First seen · 99 lines · 0 tokens per session scan A 6a9881172417
plan is a command published in the GitHub repository pinecone-io/rings (5 stars, last pushed 15d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 982 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.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.