pydantic-ai-gepa: Skill for Claude Code

.claude/skills/spec-audit/SKILL.md

spec-audit is a skill for Claude Code from indexedlabs/pydantic-ai-gepa. It costs 44 tokens per session (595 once invoked), scanned A, original, MIT.

A tool for checking and updating project specifications to a standard format built around guarantees and constraints. A specification describes what a system must do and the limits it must follow.

In plain words
What is it for?
Use it to audit a specification tree, identify non-conforming documents, and migrate older behavior-and-interface sections to the newer format.
Why use it?
It finds outdated, incomplete, or poorly structured specifications before they make planning and implementation confusing.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions Codex.

This is indexedlabs/pydantic-ai-gepa's own configuration. It tells Claude Code how to work on pydantic-ai-gepa itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything pydantic-ai-gepa configures →

Reuse

Borrowing it

Nothing to install: this file belongs to indexedlabs/pydantic-ai-gepa. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/indexedlabs/pydantic-ai-gepa/main/.claude/skills/spec-audit/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/indexedlabs/pydantic-ai-gepa

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for spec-audit

README.md
[![agentmods](https://agentmods.dev/badge/skills/indexedlabs/pydantic-ai-gepa/spec-audit/github.svg)](https://agentmods.dev/skills/indexedlabs/pydantic-ai-gepa/spec-audit)
Your own site
<a href="https://agentmods.dev/skills/indexedlabs/pydantic-ai-gepa/spec-audit"><img src="https://agentmods.dev/badge/skills/indexedlabs/pydantic-ai-gepa/spec-audit/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for spec-audit

Your own site · 80×15
<a href="https://agentmods.dev/skills/indexedlabs/pydantic-ai-gepa/spec-audit"><img src="https://agentmods.dev/badge/skills/indexedlabs/pydantic-ai-gepa/spec-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 44 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 595 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 5.1 $0.00044 $0.00595
Opus 5 $0.00022 $0.00298
Sonnet 5 $0.00009 $0.00119
Haiku 4.5 $0.00004 $0.00060

Measured 10d ago against content hash 8cd4646f7fac, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

spec-audit 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 10d 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/skills/spec-audit/SKILL.md · 75 lines

How it starts

The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Spec Audit

Overview

Systematically audit specs in the Mighty graph for format compliance, then migrate non-conforming specs to the canonical Guarantees + Constraints structure.

When to use

  • After adopting the new spec format and needing to migrate existing specs.
  • Periodic hygiene: find specs with missing sections, stale prose, or structural issues.
  • Before a major planning push: ensure the spec tree is clean and navigable.

Audit workflow

1) Scan the tree

mt tree --all

Walk each root and its children. For every spec, run mt show <id> and check against the format checklist (references/format-checklist.md).

2) Identify non-conforming specs

Flag specs that have any of:

  • ## Behaviors or ## Interfaces sections (old format)
  • Missing ## Guarantees section
  • Missing ## Constraints section (acceptable only if truly no constraints exist — annotate why)
  • Unstructured prose instead of bullet lists
  • Nesting deeper than 3 levels in the spec tree
  • Orphan specs (no parent, not a root)

3) Migrate specs

Use mt show --json <id> | jq -r '.description' to get the current description, then transform it following the migration patterns (references/migration-patterns.md).

Apply with:

cat <<'EOF' | mt update <id> --description-file -
<new description>
EOF

4) Validate tree structure

After migration, verify:

  • Max 3 levels deep (root → mid → leaf)
  • Every non-root spec has a parent via child_of edge
  • Root specs are area/capability buckets, not implementation details
  • Parent summaries still accurately describe their children

5) Batch workflow

Process in tree order — roots first, then children:

  1. Migrate root/parent specs first (they set the framing for children)
  2. Migrate children, checking consistency with parent
  3. After migrating children, re-read parent to update its summary if children changed scope
  4. Leave a comment on each migrated spec: mt comment --on <id> --content "Migrated to Guarantees + Constraints format"

Read the full file on GitHub · 75 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 10d ago First seen · 75 lines · 44 tokens per session scan A 8cd4646f7fac

Subscribe to this mod's changes

spec-audit is a skill published in the GitHub repository indexedlabs/pydantic-ai-gepa (34 stars, last pushed 16d ago), licensed MIT. It adds 44 tokens to every session and 595 once invoked, about $0.0002 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 2026-09-01.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens