work-plan

A planning tool that turns a software task into a detailed, read-only implementation plan for another developer or coding agent.

In plain words
What is it for?
It is for inspecting a project, identifying the simplest complete implementation, defining validation checks, and preparing a self-contained handoff.
Why use it?
It helps clarify the work before code changes begin and keeps the plan grounded in the existing code, constraints, tests, and reliability needs.

Skill for Claude CodeCodex

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/xcaeser/work-skill/work-plan
Any agent
npx skills add xcaeser/work-skill --skill work-plan
Clone the repo
git clone --depth 1 https://github.com/xcaeser/work-skill

Made for: Claude Code, Codex.

Per session 54 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,141 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 $0.00054 $0.01141
Opus 5 $0.00027 $0.00571
Sonnet 5 $0.00011 $0.00228
Haiku 4.5 $0.00005 $0.00114

Measured 2d ago against content hash 80a9248ef577, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

work-plan 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 2d 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.

skills/work-plan/SKILL.md · 98 lines

How it starts

The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Work / 3. Plan

Produce an implementation-ready plan without changing source files.

Make the plan protect reliability, restraint, modular boundaries, the simplest complete implementation, human authorship, clean breaks over obsolete compatibility, meaningful tests, and proof over status reports. Prefer existing dependencies and durable architecture over speculative packages or stopgaps.

Fixed route

  • If the exact subagent model, effort, or goal tools are unavailable, return blocked with the missing capability. Do not substitute a model or perform the analyst's work in the parent.
  • Launch exactly one gpt-5.6-sol subagent at xhigh effort with fork_turns: none.
  • Give it a fun call sign, the exact task statement, source of truth, read-only ownership, constraints, acceptance checks, and validation requirements.
  • Require it to inspect independently and return concrete evidence, not a status report or a claim that an unproved step is “routine.”
  • Require it to call create_goal with the exact analysis goal before inspection and update_goal complete only after the required evidence is collected.
  • Let the analyst run until it returns the plan, a real blocker, or a user-input request. Do not cancel it because a polling window or arbitrary wall-clock interval elapsed; a wait timeout is not a failure.
  • The analyst must not edit, commit, deploy, spawn, or delegate.
  • Scale depth to the task. Inspect only relevant paths, direct consumers, and evidence needed for the handoff; return the plan without process narration and stop when every required field is supported.
  • Report the successful launch as a compact table with Agent, Working on, Goal, Ownership, and Model.

Build the plan

The parent defines the mission. The analyst inspects only relevant context, traces current behavior through real consumers, and resolves evidence-backed decisions. Keep early alternatives independent; do not let the first elegant reduction become the plan without checking it against the exact task. The parent verifies paths, symbols, commands, and assumptions before returning the handoff.

Read the full file on GitHub · 98 lines

Files

What ships with it

1 file 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.

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. 2d ago First seen · 98 lines · 54 tokens per session scan A 80a9248ef577

Subscribe to this mod's changes

work-plan is a skill published in the GitHub repository xcaeser/work-skill (2 stars, last pushed 22d ago), licensed MIT. It adds 54 tokens to every session and 1,141 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 2026-08-31.

Related

Other skills, from other repositories

changes-report

Report all repository changes that entered a target branch during one required date or period, grouped by product change and written as plain English for a broad audience. Use for daily, weekly, date-range, or relative-period change summaries rather than explaining one known diff.

yarlson/yarstack · 54 tokens

jira-issue-create

Create one or more Jira issues through acli from user-approved drafts using heading-based Context, Acceptance criteria, and Engineering notes sections. Use only when explicitly invoked to create Jira issues; use jira-issue-refine when requirements still need refinement.

yarlson/yarstack · 53 tokens

claude-review

Run an independent Claude Opus review of the complete current change against the repository's default branch, then verify its findings locally. Use after focused checks pass when you want a second model to review the change before further edits or delivery.

yarlson/yarstack · 50 tokens

test-gap-review

Review whether existing tests and verification credibly prove a scoped behavior contract. Use during validation when evidence may omit important behavior or provide false confidence.

yarlson/yarstack · 32 tokens

orcast

Use when orchestrating multiple agents in Orca: fan out parallel workers, pipeline work across stages, adversarially verify findings, run judge panels or loop-until-dry sweeps, or delegate a task and get the result back. You write a Plan definition in real JavaScript — a worker-workflow graph of worker, action, and…

RubinCarter/orcast · 139 tokens

jira-issue-deliver

Autonomously deliver one Jira issue from intake to a ready GitHub pull request. Use only when the user authorizes implementation, commits, pushes, PR state changes, CI remediation, and resolution of requested automated review feedback.

yarlson/yarstack · 51 tokens