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.
curl -O https://raw.githubusercontent.com/indexedlabs/pydantic-ai-gepa/main/.claude/skills/tasks/SKILL.mdgit clone --depth 1 https://github.com/indexedlabs/pydantic-ai-gepaWrote 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.
[](https://agentmods.dev/skills/indexedlabs/pydantic-ai-gepa/tasks)<a href="https://agentmods.dev/skills/indexedlabs/pydantic-ai-gepa/tasks"><img src="https://agentmods.dev/badge/skills/indexedlabs/pydantic-ai-gepa/tasks/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.
<a href="https://agentmods.dev/skills/indexedlabs/pydantic-ai-gepa/tasks"><img src="https://agentmods.dev/badge/skills/indexedlabs/pydantic-ai-gepa/tasks.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00062 | $0.00671 |
| Opus 5 | $0.00031 | $0.00336 |
| Sonnet 5 | $0.00012 | $0.00134 |
| Haiku 4.5 | $0.00006 | $0.00067 |
Grade A, and why
tasks 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.
How it starts
The opening of the file, as written. The whole thing — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Tasks
Overview
Claim (or create) a Mighty task for the work, keep short progress comments as you go, record decisions when you choose between alternatives, then link evidence and close cleanly.
Progressive disclosure rules
- Assume
mt primehas already been run for this session; only run it if you’re missingmtconventions/context. - Prefer comments for ephemeral progress and decisions for lasting choices/constraints.
- Keep comments short and high-signal (1–5 bullets or a few sentences).
- When referencing specs/decisions/tasks in descriptions/comments, use
[label](cite:<id_prefix>-...)(always include link text).
Workflow
0) Start with context (graph first)
Start with:
mt work/mt mineto see what’s already assigned.mt search <keyword>andmt treeto find the relevant spec/decision.mt show <id>to read the current intent before changing code.
1) Ensure there is a task for the change
- If the user provides a task ID, use it.
- Otherwise create one, linking it to the source spec/decision with
--source:- Template:
references/task-template.md
- Template:
2) Claim the task (start a session)
mt claim <task-id> --reason "Starting work"
3) While working, leave lightweight breadcrumbs
Use comments for progress checkpoints and “why”:
mt comment <task-id> --content "Observed X. Choosing Y because Z. Next: A then B."
Record design decisions when you pick between alternatives:
mt decision new ... --source <task-id>(creates a spawned edge)- If you revise an existing decision, use
mt decision update ... --reason "..."
Examples: references/progress-comment-examples.md
More examples: references/examples.md
4) Link evidence for completed work
When the work is implemented/tested, link evidence (files and/or commits):
mt link --from <task-or-spec-id> --rel implemented_by --to-type file --to-ref path/to/file.py -d "Core implementation"
5) Close the task
mt task close <task-id> --reason "Done" --resolution "What changed and how to verify"
What ships with it
4 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.
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.
- 10d ago First seen · 86 lines · 62 tokens per session scan A a6f2f864e928
tasks is a skill published in the GitHub repository indexedlabs/pydantic-ai-gepa (34 stars, last pushed 15d ago), licensed MIT. It adds 62 tokens to every session and 671 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 2026-09-01.
Other skills, from other repositories
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
story-readiness
Validate that a story file is implementation-ready. Checks for embedded GDD requirements, ADR references, engine notes, clear acceptance criteria, and no open design questions. Produces READY / NEEDS WORK / BLOCKED verdict with specific gaps. Use when user says 'is this story ready', 'can I start on this story', 'is…
autotask-creator
Rules for automation CRUD from the group-chat commander. The commander does not call mutation tools and does not edit cloud/autotasks files directly. It emits one or more top-level ... containers in its final text; the bus parses and applies them after the turn.
projects
List all managed projects with status, branch, open PRs, and open issue counts — portfolio-level view.