What is adev:hygiene?

A health check for the project's context files and source code. It looks for outdated information, mismatches, missing coverage, and other maintenance problems.

Use it to run a full context audit or check one area, such as stale specifications, code drift, configuration changes, or test debt. It can fix some issues automatically.

It helps find places where project documentation and code have drifted apart before they cause confusion or implementation mistakes.

adev:hygiene — Skill by agentic-development

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/agentic-development/adev-plugin/hygiene

Any agent

npx skills add agentic-development/adev-plugin --skill hygiene

Clone the repo

git clone --depth 1 https://github.com/agentic-development/adev-plugin

Made for: Claude Code, Codex.

Per session 90 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 16,219 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.

Model	Per session	Once invoked
Fable 5	$0.00090	$0.16219
Opus 5	$0.00045	$0.08110
Sonnet 5	$0.00018	$0.03244
Haiku 4.5	$0.00009	$0.01622

Measured 2d ago against content hash bb8fc693c207, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

adev:hygiene 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.

providers/codex/skills/hygiene/SKILL.md · 1,265 lines

How it starts

The opening of the file, as written. The whole thing — 1,265 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Context Hygiene Audit

Audit the health of .context-index/ and source code, generating actionable reports. Twenty-three audit passes detect staleness, drift, coverage gaps, milestone readiness, lifecycle consistency, operational patterns, code health issues, heuristic index health, kind-discriminator validity, validate config drift, platform drift, and test-suite debt so the team can fix them before they become obstacles.

Arguments

No arguments: full audit (all twenty-three passes)
--check <type>: run a single pass (constitution, charters, adrs, samples, drift, sessions, references, governance, recoveries, blockers, milestones, lifecycle, code-health, provenance, issue-board, heuristics, code-drift, kind-validity, validate-config-drift, platform-drift, test-policy-drift, test-debt)
--pass <type>: alias for --check <type> (accepted for symmetry with related skills; identical behavior)
--fix: auto-fix issues where possible (runs /adev:sync for constitution drift, etc.)
--status <spec-path> <new-status>: manually update a spec's status field in frontmatter. Useful for correcting status when automation gets out of sync. Example: --status .context-index/specs/features/auth/login.spec.md validated

Legal status values are defined in lib/spec-status.mjs::SPEC_STATUSES. The adev/status-enum-legal diagnostic enforces this enum at write time.

Prerequisites

The project must have .context-index/ initialized. If it does not exist, suggest running /adev:init first.

Process

If --status <spec-path> <new-status> is provided:

Validate the spec path exists and is a valid spec file
Validate the new status value is in SPEC_STATUSES (imported from lib/spec-status.mjs). The seven legal values are defined there; the adev/status-enum-legal diagnostic enforces this enum at write time. Use assertLegalStatus(value) from that module to validate.
Read the spec file
Parse YAML frontmatter
Record the old status value
Update the status field to the new value
Write the spec file back
Log: "Updated spec status: {old} → {new}"

Read the full file on GitHub · 1,265 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.

agents/openai.yaml 194 B

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.

2d ago First seen · 1,265 lines · 90 tokens per session scan A bb8fc693c207

Subscribe to this mod's changes

adev:hygiene is a skill published in the GitHub repository agentic-development/adev-plugin (11 stars, last pushed 2d ago), licensed MIT. It adds 90 tokens to every session and 16,219 once invoked, about $0.0005 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.

Testing

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

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…

vercel/next.js · 95 tokens

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…

openai/codex · 114 tokens

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…

openai/codex · 113 tokens

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…

microsoft/vscode · 71 tokens

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…

vercel/next.js · 170 tokens