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/reconcilenpx skills add agentic-development/adev-plugin --skill reconcilegit 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 | $0.00086 | $0.03542 |
| Opus 5 | $0.00043 | $0.01771 |
| Sonnet 5 | $0.00017 | $0.00708 |
| Haiku 4.5 | $0.00009 | $0.00354 |
Grade A, and why
adev:reconcile 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 — 241 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Lifecycle Reconciliation
Interactive repair for mismatches between specs, plans, the issue board, and code provenance. Reads detection results from /adev:hygiene and /adev:status, then offers targeted fixes for each finding.
Announce at start: "I'm using the adev:reconcile skill to detect and repair lifecycle mismatches."
Arguments
- No arguments: full reconciliation scan (all checks)
--check <type>: run a single check (epics, plans, issues, manifests, untraced, lifecycle-sync)--batch: apply fixes without confirmation prompts (use with caution)--dry-run: show what would be fixed without making changes--fix: apply all detected fixes automatically without per-item confirmation (this is the default behavior post-check-set-restructure.spec.md)--no-fix: report-only mode — show findings without applying any fixes (opposite of the new default; preserves the historical "scan first, then ask" workflow for users who want it)
Prerequisites
.context-index/must exist withmanifest.yaml.tasks.backendmust be configured for issue board operations.- If a recent hygiene report exists at
.context-index/hygiene/drift-report.md, read it for pre-computed findings. Otherwise, run detection inline.
Process
Default mode: --fix (applies fixes automatically). Pass --no-fix for a report-only run. This default was flipped as part of check-set-restructure.spec.md so that /adev:reconcile is the authoritative repair tool for lifecycle drift (the previous validate-time Check 12 only warned; it never fixed). User-facing prompts still appear interactively unless --batch or --no-fix is passed.
Load Skill Extensions: Load any skill extension instructions before proceeding:
adev skill-ext load --skill reconcile
If the output is not __NONE__, incorporate it as additional standing instructions that apply to this skill's entire execution. Frame it as: "The following skill extension instructions apply to this invocation (source: installed domain extensions and/or project-level overrides)." If the output is __NONE__, continue normally.
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 · 241 lines · 86 tokens per session scan A d5069b2b62b5
adev:reconcile is a skill published in the GitHub repository agentic-development/adev-plugin (11 stars, last pushed 3d ago), licensed MIT. It adds 86 tokens to every session and 3,542 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…