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-deepennpx skills add CorridorTech/PoseCap --skill ad-deepengit 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 | $0.00164 | $0.01873 |
| Opus 5 | $0.00082 | $0.00937 |
| Sonnet 5 | $0.00033 | $0.00375 |
| Haiku 4.5 | $0.00016 | $0.00187 |
Grade A, and why
ad-deepen 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 — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
<background_information>
Implements ADR-0020 (doc/adr/0020-deep-modules-vocabulary.md) — operational counterpart to the WORKFLOW §8 architectural vocabulary. Surfaces deepening opportunities and walks the user through them. Process scaffold; no primary file output.
Profile scope: team and mature only. Architectural deepening is premature for ≤200-line experiments. poc and solo users do not have this skill installed; to enable deepening, re-init the project at team profile (agentic profile set team) once the codebase has stabilized enough to warrant it. Per ADR-0020 §4.
Codex auto-trigger on description keywords is less mature than Claude Code's. If auto-invocation does not fire when the user mentions deepening, shallow modules, the deletion test, or the two-adapters rule, invoke this skill manually. </background_information>
Route elsewhere when:
- The change is a one-line fix or mechanical refactor → no scaffold needed.
- The codebase is
poc-shaped (one-shot script, ≤200 lines, no callers): deepening is premature; ship the experiment first. - The friction is a bug, not a shape —
ad-diagnose(WORKFLOW §15). - The friction is a naming/vocabulary drift —
ad-domain. - The friction is missing context, not module shape —
ad-grill-me.
Step 1 — explore organically. Before naming candidates, read.
- Read
CONTEXT.mdif it exists. Anchor domain vocabulary; deepening proposals must use Customer, Order, Triage role — not Service, Handler, Manager. - Read
ARCHITECTURE.mdif it exists. Read accepted ADRs indoc/adr/covering the surface you are about to walk. - Walk the codebase noting friction:
- Concepts bouncing between modules (locality fault).
- Interfaces as wide as their implementations (shallow modules — apply the deletion test).
- Tests that mock four things to exercise one path (test-surface fault).
- Adapters with one concrete implementation (two-adapters-rule violation, if no second is planned).
Read with eyes for shape, not bugs. The friction is in module geometry; the bug-finding skill is ad-diagnose.
Step 2 — present candidates numbered. For each deepening opportunity, produce a short numbered entry:
### Candidate N: <one-line title using domain + architectural vocabulary>
**Files involved:** `src/foo.ts:42`, `src/bar.ts`.
**Friction:** <one-paragraph plain English — what hurts today, who feels it, when>.
**Proposal:** <one-paragraph plain English — what changes about the module shape>.
**Vocabulary check:** <Module / Interface / Seam / Adapter / Depth / Leverage / Locality applied here, per WORKFLOW §8>.
**Deletion test:** <if you imagine deleting the module today, what happens? Complexity vanishes → delete instead of refactoring. Complexity reappears across N callers → it earns its keep, deepen it>.
**Two-adapters check:** <if introducing a seam: name the second concrete adapter that justifies it. If only one adapter exists or is planned, the seam is hypothetical — drop it from the proposal>.
**Test surface impact:** <does the new shape make the right pattern testable at the call site? If not, the proposal is wrong-shaped>.
**ADR conflicts:** <name any accepted ADR this proposal contradicts. Flag for reopening only if the friction warrants it; otherwise the candidate is rejected>.
Number candidates 1, 2, 3, ... Order by leverage × locality (largest impact first, lowest blast radius among ties). Cap at five.
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 · 113 lines · 164 tokens per session scan A 1d9839249868
ad-deepen is a skill published in the GitHub repository CorridorTech/PoseCap (190 stars, last pushed 10d ago), licensed Apache-2.0. It adds 164 tokens to every session and 1,873 once invoked, about $0.0008 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.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
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…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.