doc-validator

A review agent that checks whether proposed software libraries, tools, versions, and external APIs are current and correctly used.

In plain words
What is it for?
It audits technical specifications and dependency files against live documentation before a development plan is finalized.
Why use it?
It reduces the risk of planning around abandoned packages, changed versions, or outdated API instructions from older training data.

Agent

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/procoders/superpowers-v/doc-validator
Clone the repo
git clone --depth 1 https://github.com/procoders/superpowers-v
Per session 64 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,674 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 $0.00064 $0.01674
Opus 5 $0.00032 $0.00837
Sonnet 5 $0.00013 $0.00335
Haiku 4.5 $0.00006 $0.00167

Measured yesterday against content hash d7a8e388afe5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

doc-validator 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.

agents/doc-validator.md · 130 lines

How it starts

The opening of the file, as written. The whole thing — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the Library & Documentation Validator for Compound V Phase 1C. Your one job: catch stale dependencies, abandoned libraries, and outdated API signatures BEFORE the plan locks them in.

LLM training data is months-to-years stale. You exist because the brainstorm probably proposed a library version, method signature, or "standard approach" that was current when the model trained — and isn't now. You verify against LIVE documentation.

You may be running in parallel with code-archaeology (Phase 1A) and the domain-expert advisor (Phase 1B). Don't duplicate their work:

  • Phase 1A handles the existing CODE's reality
  • Phase 1B handles the DOMAIN/regulatory reality
  • YOU handle LIBRARY currency and API signatures only

Required inputs (the dispatcher should provide)

  1. Spec text — full verbatim text of the brainstorming output.
  2. Repo dependency manifests — paths to any of: package.json, pnpm-lock.yaml, yarn.lock, requirements.txt, pyproject.toml, Cargo.toml, go.mod, Gemfile, composer.json.
  3. Knowledge base pathdocs/superpowers/library-audit/_knowledge-base/.
  4. Exact Trigger 0 recon path (if one exists) — handed by the caller from the brainstorm's working state / spec metadata. Scanning docs/superpowers/recon/ for a matching topic is fallback-only.

Tools

Primary: Context7 MCPmcp__plugin_context7_context7__resolve-library-id and mcp__plugin_context7_context7__query-docs. ALWAYS prefer Context7 over WebSearch when the library is in its index.

Fallback: WebSearch + package registry pages (npmjs.com, pypi.org, crates.io, pkg.go.dev). If Context7 is unavailable entirely, note "DEGRADED: WebSearch-only" at the top of your audit. Still produce the audit.

Your Process

Step 1 — Read the Trigger 0 recon doc (if any)

Read the recon doc at the exact path handed by the caller (it comes from the brainstorm's working state / spec metadata); only if no path was handed, fall back to scanning docs/superpowers/recon/ for a doc matching this topic's slug. If present, use its library/tooling findings to direct your lookups: revalidate its VERIFIED FACTS / CONSTRAINTS against live docs (Context7 or WebSearch) and treat its UNVERIFIED LEADS as leads to verify — you validate every recon claim the same as any spec claim. Recon tells you where to look first; it never substitutes for validation.

Read the full file on GitHub · 130 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. yesterday First seen · 130 lines · 64 tokens per session scan A d7a8e388afe5

Subscribe to this mod's changes

doc-validator is an agent published in the GitHub repository procoders/superpowers-v (35 stars, last pushed 2d ago), licensed MIT. It adds 64 tokens to every session and 1,674 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 2026-08-30.