What is auto_task.create_specs_from_todos?

A TODO-to-fix planning tool that reads file-and-line TODOs and turns them into a written repair plan. It investigates bugs, suggests how to verify fixes, and does not change code.

Use it to create a `tasks.md` plan for bugs or other TODOs, including likely causes, proposed fixes, and checks that would confirm the work.

It removes the need to work out the scope and order of many TODO items manually. It also records which repository each task belongs to when several repositories are involved.

auto_task.create_specs_from_todos — Skill for Claude Code by gpsaggese

Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo

git clone --depth 1 https://github.com/gpsaggese/helpers

agentmods

npx agentmods add skills/gpsaggese/helpers/auto_task.create_specs_from_todos

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/gpsaggese/helpers/auto_task.create_specs_from_todos/github.svg)](https://agentmods.dev/skills/gpsaggese/helpers/auto_task.create_specs_from_todos)

Your own site

<a href="https://agentmods.dev/skills/gpsaggese/helpers/auto_task.create_specs_from_todos"><img src="https://agentmods.dev/badge/skills/gpsaggese/helpers/auto_task.create_specs_from_todos/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/gpsaggese/helpers/auto_task.create_specs_from_todos"><img src="https://agentmods.dev/badge/skills/gpsaggese/helpers/auto_task.create_specs_from_todos.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 10 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 619 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.

Model	Per session	Once invoked
Fable 5.1	$0.00010	$0.00619
Opus 5.5	$0.00004	$0.00248
Sonnet 5.5	$0.00002	$0.00124
Haiku 4.5	$0.00001	$0.00062

Measured yesterday against content hash 380646e5dd8b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

auto_task.create_specs_from_todos 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/skills/auto_task.create_specs_from_todos/SKILL.md · 65 lines

How it starts

The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Goal

Given a list of TODOs in a file from the user, create a plan to fix them

Workflow

Understand Each TODO

Each TODO is in the form

<FILE>:<LINE_NUM>:<TODO description>

E.g.,

./helpers/hmarkdown_coloring.py:235:def colorize_bullet_points_in_slide(...

Read each TODO and understand the problem
If it's a bug:
- Find the root cause
- Run experiments to verify the issue and its root cause
Devise a plan to fix the problem and a plan to verify the fix

Write the Fix Plan

Create a plan tasks.md using the template .claude/templates/auto_task.template.md
Fill in the template's * Repo: checklist per .claude/skills/auto_task.rules.md section "Multi-Repo Issues, Branches, and PRs" (how to tell which repo a <FILE> belongs to, and how to handle TODOs spanning more than one repo)

Say in the plan file how it was generated, with this comment at the top:

<!-- Generated by `.claude/skills/auto_task.create_specs_from_todos/SKILL.md` -->

Write the comments as bullet points per .claude/skills/markdown.rules.md and .claude/skills/text.rules.md, with minimal text
Do not change the code, only propose the fixes

Follow the Conventions

Follow .claude/skills/auto_task.rules.md section "Follow the Coding and Testing Rules"
- Refer to .claude/skills/coding.*/SKILL.md and .claude/skills/testing.*/SKILL.md for the repo's best practices
For bugs, add unit tests that fail before the fix and pass after it (red/green approach)
For renaming, check the entire code base so everything is updated
- Follow .claude/skills/coding.rename/SKILL.md
For a change of function signature, update all the calling instances

Rank the Issues

Order the issues by increasing complexity, starting with the fixes of high confidence

Verification

tasks.md contains one issue block per input TODO
Every issue block has type, reason, proposed fix, confidence, complexity, and verification plan filled in
Issues are ordered by increasing complexity, starting from the highest confidence fixes
No code was changed, only the plan file was written
The plan file says that it was generated by .claude/skills/auto_task.create_specs_from_todos/SKILL.md

Read the full file on GitHub · 65 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.

yesterday First seen · 65 lines · 10 tokens per session scan A 380646e5dd8b

Subscribe to this mod's changes

auto_task.create_specs_from_todos is a skill published in the GitHub repository gpsaggese/helpers (158 stars, last pushed today), licensed Apache-2.0. It adds 10 tokens to every session and 619 once invoked, about $0.0000 per session on Opus 5.5. 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 2026-11-06.

Planning

auto_task.create_specs_from_todos next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
auto_task.create_specs_from_todosgpsaggese/helpers	Skill	158	today	Apache-2.0	A	10	Claude Code
imagegenopenai/codex	Skill	134k	today	Apache-2.0	A	113	Codex
local-ai-agentsmicrosoft/ai-agents-for-beginners	Skill	79k	today	MIT	A	200	Claude Code, Codex
playwright-climicrosoft/playwright	Skill	99k	today	Apache-2.0	A	19	Claude Code
systematic-debuggingobra/superpowers	Skill	314k	3d ago	MIT	A	21	Claude Code
next-cache-components-adoptionvercel/next.js	Skill	143k	today	MIT	A	95	Claude Code
chat-pet-sprite-creationmicrosoft/vscode	Skill	195k	today	MIT	A	53	Claude Code, Codex