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/documentnpx skills add agentic-development/adev-plugin --skill documentgit 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 | $0.00083 | $0.01389 |
| Opus 5 | $0.00042 | $0.00694 |
| Sonnet 5 | $0.00017 | $0.00278 |
| Haiku 4.5 | $0.00008 | $0.00139 |
Grade A, and why
adev:document scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 188 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Generate Developer Documentation
Produce human-readable documentation in docs/ from .context-index/ artifacts.
Arguments
- No arguments: generate all documentation
--module <slug>: regenerate onlydocs/modules/<slug>.md- Validate slug matches pattern
^[a-z0-9_-]+$— exit 1 if invalid - Prevent path traversal: reject slugs containing ".." or use path.resolve to normalize and verify it stays within docs/modules/
- Check slug exists in manifest — exit 1 with error " not found in manifest" if missing
- Validate slug matches pattern
--check: compute what would change, output diff without writing--force: regenerate all sections unconditionally
Precondition Checks
- Check
.context-index/hygiene/dependency-graph.jsonexists- If missing: exit 1 with error "Run /adev:repomap first to generate dependency-graph.json"
- Check
.context-index/hygiene/symbol-ranks.jsonexists (symbol index)
- If missing: exit 1 with error "Run /adev:repomap first to generate symbol-ranks.json"
- Check
.context-index/manifest.yamlexists- If missing: exit 1 with error "Run /adev:init first to generate manifest.yaml"
- If
docs/does not exist, create it
Marker Protocol
Every file uses two-zone layout:
[generated content — owned by /adev:document]
<!-- adev:generated -->
<!-- adev:human -->
[human content — owned by developer, never overwritten]
Rules:
| Condition | Action |
|---|---|
| Both markers present | Preserve content after <!-- adev:human -->, regenerate before |
Only <!-- adev:human --> |
File is human-owned, do NOT overwrite |
Only <!-- adev:generated --> |
Regenerate entire file |
| Neither marker | Write fresh with both markers |
Step 1: Generate docs/architecture.md
1.1 Load Inputs
| File | Required | Purpose |
|---|---|---|
dependency-graph.json |
Yes | Module dependency edges |
symbol-ranks.json |
Yes | Exported symbols ranked by reference |
manifest.yaml |
Yes | Module list, project metadata |
constitution.md |
Optional | Project principles |
platform-context.yaml |
Optional | Runtime environment |
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 · 188 lines · 83 tokens per session scan A 09576cfef94f
adev:document is a skill published in the GitHub repository agentic-development/adev-plugin (11 stars, last pushed 2d ago), licensed MIT. It adds 83 tokens to every session and 1,389 once invoked, about $0.0004 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…