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/agentic-development/adev-plugin/worknpx skills add agentic-development/adev-plugin --skill workgit clone --depth 1 https://github.com/agentic-development/adev-pluginWhat 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 | $0.00116 | $0.05389 |
| Opus 5 | $0.00058 | $0.02694 |
| Sonnet 5 | $0.00023 | $0.01078 |
| Haiku 4.5 | $0.00012 | $0.00539 |
Grade A, and why
adev: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 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.
How it starts
The opening of the file, as written. The whole thing — 341 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Work — the Single Front Door
Classify incoming work, detect in-progress project state, route to the correct /adev:* skill, and — when the user wants — drive the lifecycle through to completion so they never have to choose another command. This is the single entry point to adev: use it whenever the user is unsure which skill to invoke, is starting new work, or is resuming.
Two things distinguish this skill from a plain router:
- It reads state first. It resumes in-progress work by proposing the next lifecycle step, not by re-asking what to do.
- It stays with the work (Conductor Mode). After a stage completes it proposes — or drives — the next stage, instead of dropping the user back to an empty prompt. See "Conductor Mode" below.
Announce at start: "I'm using the adev:work skill as your front door — I'll figure out the right step and can drive it through."
Arguments
- No arguments: interactive triage (scans state, asks what you are working on)
- Free-text description: classify the description and propose a route (e.g.,
/adev:work fix the broken test in hooks) --intake [<description>]: intake mode — classify and triage an incoming work request into an issue on the issue board--intake --file <path>: batch intake mode — read a file containing multiple requests and process them all. File must be UTF-8 text, limited to 100KB
Prerequisites
Check that .context-index/ exists. If it does not:
This project has not been initialized with the Agentic Development Framework. Run
/adev:initfirst to set up the context index, then come back.
Stop processing. No other steps run.
Step 1: Project State Scan
Scan for in-progress work using parallel tool calls in a single round:
- In-progress execution state: Call
readExecutionState(projectRoot)from<ADEV_ROOT>/lib/execution-state.mjs. Ifstatus === "active"orstatus === "blocked", the project has resumable work — surface theplanRef,currentTask, and anyblockersto the user.
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.
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.
- 2d ago First seen · 341 lines · 116 tokens per session scan A b690d76785ea
adev:work is a skill published in the GitHub repository agentic-development/adev-plugin (11 stars, last pushed 2d ago), licensed MIT. It adds 116 tokens to every session and 5,389 once invoked, about $0.0006 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.
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…