Borrowing it
Nothing to install: this file belongs to causify-ai/helpers. 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/causify-ai/helpers/master/.claude/skills/auto_task.create_plan_for_feature/SKILL.mdgit clone --depth 1 https://github.com/causify-ai/helpersWrote 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/causify-ai/helpers/auto_task.create_plan_for_feature)<a href="https://agentmods.dev/skills/causify-ai/helpers/auto_task.create_plan_for_feature"><img src="https://agentmods.dev/badge/skills/causify-ai/helpers/auto_task.create_plan_for_feature/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/causify-ai/helpers/auto_task.create_plan_for_feature"><img src="https://agentmods.dev/badge/skills/causify-ai/helpers/auto_task.create_plan_for_feature.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00016 | $0.01512 |
| Opus 5.5 | $0.00006 | $0.00605 |
| Sonnet 5.5 | $0.00003 | $0.00302 |
| Haiku 4.5 | $0.00002 | $0.00151 |
Grade A, and why
auto_task.create_plan_for_feature 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 4d 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 — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Goal
- Given a request from the user to implement a complex feature or component, break it into an ordered sequence of small, reviewable PRs, and write a full spec for every PR complex enough to need one, without implementing any code
Input
- The user passes a description of the feature/component to implement and optionally an existing plan file to extend
When to Use This Skill
- Use it when one request is too large for a single PR: it needs more than one logical, independently reviewable change, and at least one of those changes has a design decision worth writing down
- For a request that already fits in one PR, skip straight to "Write a Spec for a PR" below, with that PR being the whole request
Workflow
Understand the Request
- Read related code in the codebase and existing code in the target directory
- If the user references a roadmap/plan file (e.g.,
plan.<TOPIC>.md), read it to extract the exact scope of the requested PR/feature - If an architecture doc already exists for the target directory, read it to understand the current design
- If the problem or the desired solution is not perfectly clear, follow
.claude/skills/auto_task.rules.mdsection "Ask for Clarification Before Executing an Unclear Plan" before decomposing anything
Decompose into PRs
- Break the feature into an ordered sequence of small, cohesive PRs; each PR must be reviewable and testable on its own
- Prefer PRs that change whole files over splitting one file's logic across multiple PRs
- State each PR's dependency on the PRs before it explicitly; do not leave a dependency implicit
- Merge PRs that are individually low risk and low complexity into one PR instead of over-fragmenting the sequence
Decide Which PRs Need a Full Spec
- A PR needs a full spec when it introduces a new interface (class, function, CLI flag), makes a non-obvious design decision or trade-off, or carries meaningful risk (touches shared/core code, hard to reverse, many call sites)
- A small, mechanical, low-risk PR (rename, config tweak, adding a test) does not need one; its bullet description in the plan is enough
- For every PR that needs one, write its spec by following "Write a Spec for a
PR" below, passing it
<TOPIC>_PR<NUM>as the topic and pointing it at the plan file written below so it can read the PR's exact scope- This produces
spec.<TOPIC>_PR<NUM>.mdfor that PR
- This produces
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.
- 4d ago First seen · 138 lines · 16 tokens per session scan A 581b391a357d
auto_task.create_plan_for_feature is a skill published in the GitHub repository causify-ai/helpers (150 stars, last pushed today), licensed Apache-2.0. It adds 16 tokens to every session and 1,512 once invoked, about $0.0001 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 2026-10-13.
Other skills, from other repositories
create-pr
Creates a GitHub PR with a Linear-ticket-prefixed title and a decision-led, narrative description for Prisma 8. Use when the user wants to create a pull request, open a PR, or submit changes for review.
git-commit
Generate well-formatted git commit messages following conventional commit standards.
repo-sync
Manage automatic Git syncing on macOS with repo-sync. Use only when the user explicitly invokes /repo-sync.
mcore-split-pr
Split a PR into multiple PRs to reduce the number of required CODEOWNERS reviewer groups.
contributing
How to contribute to evlog, covering commit and PR conventions, changesets, the Definition of Done, testing rules, and the authored skills that walk through building a new adapter, enricher, framework integration, or map rule. Load this for any question about contributing, opening a PR, or adding something to the…
git-commit-writer
Trigger when the user asks to write a commit message, generate a commit from staged changes, review a diff before committing, or says "/commit". Reads git diff --staged and produces an opinionated, convention-matching commit message.