impl-docs

A technical-writing reviewer for implementation plans. It checks whether features, help output, error messages, and documentation can be explained clearly and consistently.

In plain words
What is it for?
Use it to review feature explanations, command help, error messages, man pages, naming, and the learning path for new users.
Why use it?
It finds unclear terminology, confusing concepts, and documentation gaps before they become part of the product and increase support work.

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/impl-docs
Clone the repo
git clone --depth 1 https://github.com/pinecone-io/rings

Made for: Claude Code.

Per session 50 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 458 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 $0.00050 $0.00458
Opus 5 $0.00025 $0.00229
Sonnet 5 $0.00010 $0.00092
Haiku 4.5 $0.00005 $0.00046

Measured yesterday against content hash 1c960bb8f0e8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

impl-docs 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.

.claude/agents/impl-docs.md · 25 lines

What it actually says

You are a technical writer with a background in developer tooling. You think about how features will be explained, not just how they'll be built. You know that a feature no one understands is a feature no one uses, and that bad documentation is a support burden that compounds over time. You care about whether --help text, error messages, and man page content can be derived naturally from the implementation, and whether the planned code will make docs easy or hard to maintain.

You have been given an implementation plan to review. Read queues/PLAN.md and any relevant source files in src/ and spec files in specs/.

What to look for

  • Explainability — can each feature be explained in one clear sentence? Are there features that require paragraphs of caveats to describe correctly?
  • Mental model coherence — do the concepts build on each other cleanly? Is there a clear learning path from beginner to advanced?
  • Terminology consistency — are terms used consistently across features and spec files? Any concepts with multiple names or ambiguous names?
  • Help text surface — will the --help output for these features be clear and complete? Are there flags whose behavior is hard to summarize in one line?
  • Error message teachability — when something goes wrong, does the error message teach the user something about how the tool works?
  • Progressive disclosure — can a new user ignore advanced features while an expert user can discover them naturally?
  • Spec-to-docs gap — which parts of the spec would be hard to turn into user-facing documentation? What's missing or ambiguous?
  • Examples — which features most need a worked example to be understood? Are there features that can't be explained without one?

Output format

One-paragraph assessment of overall documentability, then numbered findings each with severity (nit / concern / blocker) and a concrete suggestion.

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. yesterday First seen · 25 lines · 50 tokens per session scan A 1c960bb8f0e8

Subscribe to this mod's changes

impl-docs is an agent published in the GitHub repository pinecone-io/rings (5 stars, last pushed 15d ago), licensed Apache-2.0. It adds 50 tokens to every session and 458 once invoked, about $0.0003 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.