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/corridortech/posecap/ad-nextnpx skills add CorridorTech/PoseCap --skill ad-nextgit clone --depth 1 https://github.com/CorridorTech/PoseCapWhat 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 | $0.00111 | $0.02732 |
| Opus 5 | $0.00056 | $0.01366 |
| Sonnet 5 | $0.00022 | $0.00546 |
| Haiku 4.5 | $0.00011 | $0.00273 |
Grade A, and why
ad-next 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 — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
<background_information>
Read-only state survey + prioritized next-action recommendations. Mirrors flutter doctor shape: layer-by-layer status + concrete fix per finding. Complements ad-drift — audit answers "is anything wrong?", next answers "what should I do?".
The skill writes nothing. Output is recommendations the user copies into the next conversation turn or the next CLI invocation.
Codex auto-trigger on description keywords is less mature than Claude Code's. If auto-invocation does not fire when the user asks about workflow status, invoke this skill manually. </background_information>
Do not parse skill bodies. Do not run tests. Do not invoke other skills.
Step 1 — classify scenario before ranking. Layer status is evidence; scenario determines the right next step.
- Fresh / unframed greenfield: no durable product framing, even if a framework scaffold or a few early files already exist. This is a product-framing problem, not an
AGENTS.mdproblem. - Product-framed greenfield: PRD exists, but no meaningful code yet. This is where
/ad-bootstrap,/ad-guidelines, optional/ad-design, then/ad-specbecome the normal sequence. - Brownfield: meaningful code exists and the scan can summarize the current product behavior. Existing code can supply product and architecture evidence;
/ad-bootstrapis scan-first here and may precede PRD backfill. - Feature planning: PRD/spec artifacts exist and have downstream gaps (accepted PRD with no specs, accepted spec with no tasks).
- Implementation in progress: dirty tree, branch ahead of
main, in-progress tasks, blocked tasks, or proposed ADRs. - Maintenance / install hygiene: stale kit state, profile/install mismatch, missing expected conditional skills.
If scenarios overlap, report the strongest active scenario in this order: implementation in progress, maintenance/install hygiene, feature planning, product-framed greenfield, brownfield, fresh/unframed greenfield. If code exists but product behavior cannot be summarized, choose fresh/unframed greenfield rather than brownfield.
Step 2 — layer-by-layer status. Render six sections in this exact order. Use words for status (present, in flight, missing, stale) — no emoji.
Layer 1 — Constitution: WORKFLOW.md (kit-shipped), AGENTS.md / CLAUDE.md (operational guide), GUIDELINES.md (full engineering reference). AGENTS.md missing is not the first greenfield finding when product framing is missing; recommend product discovery / PRD first, then /ad-bootstrap.
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 · 112 lines · 111 tokens per session scan A 236f544ed8ee
ad-next is a skill published in the GitHub repository CorridorTech/PoseCap (190 stars, last pushed 10d ago), licensed Apache-2.0. It adds 111 tokens to every session and 2,732 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
orca-emulator-android
Control an Android emulator / device from inside Orca using the orca CLI. Use for listing/booting AVDs, taps, swipes, typing, hardware buttons (incl. Back and Recents), rotation, app install/launch, runtime permissions, the accessibility tree, and logcat — driving a real adb-connected device or emulator.…
android-tombstone-symbolication
Symbolicate the .NET runtime frames in an Android tombstone file. Extracts BuildIds and PC offsets from the native backtrace, downloads debug symbols from the Microsoft symbol server, and runs llvm-symbolizer to produce function names with source file and line numbers. USE FOR triaging a .NET MAUI or Mono Android app…
git-safety
Git safety rules. INVOKE WHEN: git push, force push, git reset, git clean, destructive git, push force, reset hard. NEVER force push or do destructive git operations.
dogfood
Systematically explore and test a mobile app on iOS/Android with agent-device to find bugs, UX issues, and other problems. Use when asked to dogfood, QA, exploratory test, find issues, bug hunt, or test this app on mobile.
release
Cut a sim-use release end-to-end. Use when the user runs /release or asks to "ship a release", "publish a version", "cut a release", or "release to homebrew". Drives scripts/local-release.sh; never reimplement its build/sign/tarball logic.
android-pentest
安卓应用渗透测试 — APK分析、Hook、自动化测试、运行态驱动、签名恢复、抓包分析.