autoplan

A read-only checker for a pipeline.yaml file, which describes connected stages of automated work. It checks the file's structure, task order, referenced skills, and required conditions without changing anything.

In plain words
What is it for?
Use it after editing a pipeline, before deploying it, or after adding pipeline stages to verify that the file is valid and has no circular task dependencies.
Why use it?
It catches configuration problems before deployment or before the pipeline runs and fails.

Skill for Claude CodeCodex

Part of the agent-dev plugin — 39 skills shipped together

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/abilityai/abilities/autoplan
Any agent
npx skills add Abilityai/abilities --skill autoplan
Clone the repo
git clone --depth 1 https://github.com/Abilityai/abilities

Made for: Claude Code, Codex.

Or install agent-dev, the plugin that ships this one along with the rest of its 39 skills.

Per session 25 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,119 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00025 $0.01119
Opus 5 $0.00013 $0.00560
Sonnet 5 $0.00005 $0.00224
Haiku 4.5 $0.00003 $0.00112

Measured 3d ago against content hash 5511d5c26166, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

autoplan 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 3d 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.

plugins/agent-dev/skills/autoplan/SKILL.md · 136 lines

How it starts

The opening of the file, as written. The whole thing — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Autoplan

ℹ️ First, set expectations: before anything else, print one short line with this skill's version and its most recent change — the top entry of metadata.changelog above — e.g. autoplan vX.Y — recent: <summary>. Then proceed.

Analyze an open issue before touching any files. Reads the affected skill's SKILL.md, understands the current behavior, and produces a focused implementation plan. Run this after /claim and before /adjust-playbook or /create-playbook.

State Dependencies

Source Location Read Write Description
GitHub Issues Current repo Yes No Issue to analyze
SKILL.md files .claude/skills/*/SKILL.md Yes No Current playbook behavior
CLAUDE.md ./CLAUDE.md Yes No Agent identity and constraints

Process

Step 1: Identify the Issue

If $ARGUMENTS provided: load that issue number.

If no argument: find current in-progress issue:

gh issue list --label "status:in-progress" --state open --json number,title,body,labels --limit 1

If none in-progress, ask user to provide an issue number or run /claim first.

Step 2: Load the Issue

gh issue view $NUMBER --json number,title,body,labels

Step 3: Identify Affected Skill

Look for a skill:* label on the issue. Extract the skill name.

If no skill label:

  • Infer from the issue title/body (e.g., "fix claim flow" → likely claim)
  • Confirm with user: "This looks like it affects claim. Is that right, or is it project-level?"

If project-level (no specific skill): note that and skip to Step 6.

Step 4: Read the Affected Skill

cat .claude/skills/$SKILL_NAME/SKILL.md

If skill doesn't exist yet (this is a new skill issue), note that and skip to Step 5b.

Step 5a: Analyze the Change (existing skill)

Compare the issue requirements against the current SKILL.md. Identify:

What section(s) change:

  • Frontmatter (name, description, tools, automation type)?
  • A specific step in the Process?
  • A new step added?
  • Output format changes?
  • Error handling?

Read the full file on GitHub · 136 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.

  1. 3d ago First seen · 136 lines · 25 tokens per session scan A 5511d5c26166

Subscribe to this mod's changes

autoplan is a skill published in the GitHub repository Abilityai/abilities (11 stars, last pushed 15d ago), licensed MIT. It adds 25 tokens to every session and 1,119 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 2026-08-30.

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

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens