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.
npx agentmods add skills/wrannaman/agentic-engineering/worknpx skills add wrannaman/agentic-engineering --skill workgit clone --depth 1 https://github.com/wrannaman/agentic-engineeringWhat 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 | $0.00013 | $0.00767 |
| Opus 5 | $0.00006 | $0.00383 |
| Sonnet 5 | $0.00003 | $0.00153 |
| Haiku 4.5 | $0.00001 | $0.00077 |
Grade A, and why
work 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.
How it starts
The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Work Skill
Execute an implementation plan step by step with verification.
Announce at start: "I'm using the work skill to implement this plan."
Better with subagents: If the platform supports subagents, the subagent route produces higher quality output. See Step 4.
Input
/work <harness-dir(.claude|.codex)>/plans/2025-01-07-feature-name.md
Step 1: Load & Review Plan
- Read the plan file
- Review critically — identify questions or concerns before starting
- If concerns: raise with user before proceeding
- If no concerns: create TodoWrite task list from steps
- Extract and note:
- All implementation steps (full text — needed for subagent route)
- Validation Methodology section (primary validation command)
- PR Stack section (branch names and step boundaries)
Step 2: Worktree Setup
- Check existing worktrees:
git gtr list - Derive branch name from plan filename (
2026-03-06-add-auth.md→feat/add-auth) - If matching worktree exists → AskUserQuestion: Use existing? Create new? Work in current dir?
- If no matching worktree → AskUserQuestion: Create worktree? Work in current dir?
- Create → invoke
/worktree create <branch> - Use existing →
cdinto it, copy<harness-dir(.claude|.codex)>/plans/if missing
- Create → invoke
CRITICAL: Always use cwd for file operations — never paths from config.toml. This breaks in worktrees where cwd differs from toolkit_directory.
Step 3: Initialize Stack
Parse the PR Stack table from the plan, then detect the active stack workflow:
list_kb_documentsfor partitiongit-stacksread_kb_document_by_pathfor/index.md- Run dedicated-client checks from
/index.md; classifynative-gitif no dedicated client found - Load matching client doc before running any stack command:
charcoal→/charcoal.md,git-town→/git-town.md,native-git→/native-git.md
- Check current branch:
git branch --show-current - If on main/trunk, create or switch to the first PR branch using the detected workflow
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 · 77 lines · 13 tokens per session scan A cfd469bbcdb7
work is a skill published in the GitHub repository wrannaman/agentic-engineering (2 stars, last pushed 4mo ago), licensed MIT. It adds 13 tokens to every session and 767 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 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…