pydantic-ai-gepa: Agent for Claude Code

.claude/agents/explore-specs.md

explore-specs is an agent for Claude Code from indexedlabs/pydantic-ai-gepa. It costs 25 tokens per session (244 once invoked), scanned A, original, MIT.

An investigation guide for searching a project’s specifications graph, which links requirements, decisions, evidence, and tasks. It tells the agent how to gather the context behind code changes.

In plain words
What is it for?
Use it when investigating a change: search related specifications, follow their links, and report the relevant IDs, reasoning, and open tasks.
Why use it?
It helps explain why a design exists instead of examining code without its surrounding decisions. It also identifies related unfinished work.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

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/agents/explore-specs.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 explore-specs

README.md
[![agentmods](https://agentmods.dev/badge/agents/indexedlabs/pydantic-ai-gepa/explore-specs/github.svg)](https://agentmods.dev/agents/indexedlabs/pydantic-ai-gepa/explore-specs)
Your own site
<a href="https://agentmods.dev/agents/indexedlabs/pydantic-ai-gepa/explore-specs"><img src="https://agentmods.dev/badge/agents/indexedlabs/pydantic-ai-gepa/explore-specs/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 explore-specs

Your own site · 80×15
<a href="https://agentmods.dev/agents/indexedlabs/pydantic-ai-gepa/explore-specs"><img src="https://agentmods.dev/badge/agents/indexedlabs/pydantic-ai-gepa/explore-specs.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 25 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 244 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.
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 $0.00025 $0.00244
Opus 5 $0.00013 $0.00122
Sonnet 5 $0.00005 $0.00049
Haiku 4.5 $0.00003 $0.00024

Measured 8d ago against content hash 81def3d6f2f9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

explore-specs 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 8d 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/agents/explore-specs.md · 30 lines

What it actually says

You search the specs graph for context about code changes and decisions.

When invoked with a query:

  1. Run mt search <keywords> to find related specs, decisions, and tasks
  2. For each relevant result, run mt show <id> to get full context
  3. Follow edges to understand relationships (parent specs, linked decisions, evidence)
  4. Summarize what you found

Your response MUST include:

  • Relevant IDs: List all spec-, dec-, task-* IDs that relate to the query
  • Context: What spec does this code implement? What decisions explain the approach?
  • Open work: Any related tasks or future work planned?

Example output format:

Relevant IDs: spec-abc, spec-xyz, dec-123, task-456

Context: spec-abc (Feature X) is the parent spec. dec-123 explains why we chose approach Y.

Open tasks: task-456 tracks a follow-up enhancement.
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. 8d ago First seen · 30 lines · 25 tokens per session scan A 81def3d6f2f9

Subscribe to this mod's changes

explore-specs is an agent published in the GitHub repository indexedlabs/pydantic-ai-gepa (34 stars, last pushed 14d ago), licensed MIT. It adds 25 tokens to every session and 244 once invoked, about $0.0001 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.