agentmods.dev

task-plan.skeleton

task-plan.skeleton is a command for Claude Code from varienos/agentic-workflow. It costs 0 tokens per session (4,410 once invoked), scanned A, original, MIT.

A command template for creating a detailed implementation plan from a software request. It asks for several interpretations, alternatives, codebase analysis, and carefully considered steps before changes are made.

In plain words
What is it for?
Use it for requests such as adding a “remember me” option to a login page. It helps analyze the codebase, compare possible solutions, and outline the work needed.
Why use it?
It helps turn a broad request into an actionable plan and exposes unclear assumptions or missed alternatives before development begins.

Command for Claude Code

Written for Claude Code: a Claude Code command (commands/*.md). Also seen: mentions CLAUDE.md.

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is 1. **Do not write config into Codebase** — Only `.claude/`, `CLAUDE.md`, `.mcp.json`, and `.claude-ignore` files are allowed in the Agentbase directory. Writing.

not rated 59repo changed 1mo ago A scan 0 tokens original MIT

Good fit Use it for requests such as adding a “remember me” option to a login page. It helps analyze the codebase, compare possible solutions, and outline the work needed.

Compare 6 commands from other repositories ↓
View source ↗ varienos/agentic-workflow
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/varienos/agentic-workflow
agentmods
npx agentmods add commands/varienos/agentic-workflow/task-plan.skeleton

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 task-plan.skeleton

README.md
[![agentmods](https://agentmods.dev/badge/commands/varienos/agentic-workflow/task-plan.skeleton/github.svg)](https://agentmods.dev/commands/varienos/agentic-workflow/task-plan.skeleton)
Your own site
<a href="https://agentmods.dev/commands/varienos/agentic-workflow/task-plan.skeleton"><img src="https://agentmods.dev/badge/commands/varienos/agentic-workflow/task-plan.skeleton/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 task-plan.skeleton

Your own site · 80×15
<a href="https://agentmods.dev/commands/varienos/agentic-workflow/task-plan.skeleton"><img src="https://agentmods.dev/badge/commands/varienos/agentic-workflow/task-plan.skeleton.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,410 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 $0.00000 $0.04410
Opus 5.5 $0.00000 $0.01764
Sonnet 5.5 $0.00000 $0.00882
Haiku 4.5 $0.00000 $0.00441

Measured 1mo ago against content hash 307e5fbb8521, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

task-plan.skeleton 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 1mo 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.

Agentbase/templates/core/commands/task-plan.skeleton.md · 463 lines

How it starts

The opening of the file, as written. The whole thing — 463 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Task Plan — High-Level Task Creator

Analyzes the codebase deeply to create high-quality tasks. Usage: /task-plan <request>, /task-plan "login page remember me add"

ULTRATHINK MODE — This command works with maximum comprehension depth.

  • TAKE YOUR TIME. Think before acting.
  • Superficial analysis IS PROHIBITED. Verify assumptions and consider alternatives.
  • If something appears "obvious", prove why it's obvious.
  • If the first solution that comes to mind is likely incomplete, think of at least three alternative solutions.
  • This command should be executed with the OPUS model. Using Sonnet for task-plan execution IS PROHIBITED.

HARD GATE — Post-create /task-plan-review

This command creates the task. It does not finish the plan.

Not enough Required
Self-review, then the user report Step 6 runs /task-plan-review on every new task
"Self-review is enough" Notes contain [TASK_PLAN_REVIEW] and an overall result
User report before Step 6 Read and follow the task-plan-review command body first

Self-review does not score the planner. The scorecard is written only by /task-plan-review, and only in the user report. If Step 6 was skipped, do not tell the user the plan is ready.

Step 0 — Ultrathink: Deep Comprehension Phase

This phase IS MANDATORY. It cannot be skipped. The result will not be shown to the user, but it will guide subsequent steps.

Read the full file on GitHub · 463 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. 1mo ago Changed · +15 lines scan C → A 307e5fbb8521
  2. 2mo ago First seen · 448 lines · 0 tokens per session scan C b77e0387b36e

Subscribe to this mod's changes

task-plan.skeleton is a command published in the GitHub repository varienos/agentic-workflow (59 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 4,410 tokens. 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.

Claude CodeCode reviewPlanningagentic-workflowai-developmentautomationbacklog
Related

task-plan.skeleton compared with commands from other repositories

task-plan.skeleton next to 6 commands from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
task-plan.skeletonvarienos/agentic-workflowCommand591mo agoMITA0Claude Code
review-pryonatangross/orchestkitCommand299todayMITA48Claude Code, Cursor
review-artifact-commentsyonatangross/orchestkitCommand299todayMITA45Claude Code, Cursor
gh-security-reviewsynaptiai/synapti-marketplaceCommand7yesterdayApache-2.0A13Claude Code
review-decidegosha70/code-copilot-teamCommand7yesterdayMITA0Claude Code
feolehsvyrydov/AI-development-teamCommand1919d agoMITA17Claude Code
archolehsvyrydov/AI-development-teamCommand1919d agoMITA15Claude Code