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/samplenpx skills add agentic-development/adev-plugin --skill samplegit 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 | $0.00087 | $0.03159 |
| Opus 5 | $0.00044 | $0.01580 |
| Sonnet 5 | $0.00017 | $0.00632 |
| Haiku 4.5 | $0.00009 | $0.00316 |
Grade A, and why
adev:sample 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 — 258 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Golden Sample Curation
Scan the codebase for exemplary implementations, score candidates against the constitution and declared patterns, and extract annotated golden samples into .context-index/samples/. Golden samples are the "show, do not tell" layer of the context index: they give subagents a concrete reference for how to write code in this project.
Arguments
--pattern <name>: extract a golden sample for a specific specialist pattern (e.g.,--pattern api-route)--from <file>: promote a specific file directly to golden sample (skips discovery, goes to scoring)--score: re-score all existing samples against the current constitution and patterns--refresh: re-score, flag stale samples, and update or remove invalid ones
Prerequisites
The project must have .context-index/ initialized with constitution.md and manifest.yaml. If either is missing, stop and suggest running /adev:init first.
Process
Announce at start:
Starting golden sample curation.
Mode: [discovery | promote <file> | score | refresh]
Step 1: Load Context
Read these files once at the start. They define what "good" looks like for this project.
.context-index/constitution.md— Extract the Coding Standards section. This is the primary quality rubric..context-index/manifest.yaml— Extract thespecialistsregistry. Each specialist'strigger_patternsandtrigger_keywordsdefine domain-specific quality expectations..context-index/platform-context.yaml— If it exists, read framework conventions, file structure expectations, and naming patterns. If it does not exist, skip.- Existing samples. List all files in
.context-index/samples/. Read their frontmatter to understand what patterns are already covered and their current scores.
If --pattern was provided, filter the specialist registry to only the matching specialist. If the pattern name does not match any specialist, report the available patterns and stop.
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 · 258 lines · 87 tokens per session scan A f5c2e0376c97
adev:sample is a skill published in the GitHub repository agentic-development/adev-plugin (11 stars, last pushed 2d ago), licensed MIT. It adds 87 tokens to every session and 3,159 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…