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-reviewnpx skills add CorridorTech/PoseCap --skill ad-reviewgit 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 | $0.00309 | $0.04262 |
| Opus 5 | $0.00154 | $0.02131 |
| Sonnet 5 | $0.00062 | $0.00852 |
| Haiku 4.5 | $0.00031 | $0.00426 |
Grade B, and why
ad-review scanned grade B with 1 finding 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 3d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
NOTE: the [agents] block in ~/.codex/config.toml is for global subagent How it starts
The opening of the file, as written. The whole thing — 257 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mechanical shape:
THIS SESSION:
1. Scope the review (which range / PR / commit?).
2. Read Standards sources (AGENTS.md, ARCHITECTURE.md, GUIDELINES.md, CONTEXT.md, accepted ADRs).
3. Read Spec source (task Acceptance Criteria → spec → PRD → issue body).
4. Write the assembled context to .agentic/reviews/<ISO>-<scope>.md (audit trail).
5. Perform the review in this session. Output findings under two headings:
## Standards Findings (bugs, coupling, edge cases, doc violations)
## Spec Findings (missing requirements, scope creep, wrong impl vs quoted spec line)
6. End with a one-line aggregate (counts per axis + worst finding).
The two-axis split is structural rigor — same reviewer, but findings must be classified before mixing. A change that passes Spec can still fail Standards (and vice versa); reporting axes separately prevents one from masking the other.
<background_information>
Implements WORKFLOW §10 (Reviewer With Adversarial Discipline). On Claude Code, §10 is delivered via two parallel Task subagent calls with fresh context. On Codex, the skill defaults to structural axis separation inside a single review pass and ships a bundled fresh-context-reviewer TOML for explicit user-spawned escalation. The inline reviewer cannot rationalize a Spec pass as covering Standards (or vice versa) because the output schema forces both lists to be produced separately.
The two-axis dichotomy is borrowed from mattpocock/skills/review and bound to this kit's six-layer artifact stack (Constitution → Domain → Product → Spec → Plan/Decisions → Code).
For Codex users who want true fresh-context review (the §10 ideal), spawn the bundled subagent manually after the skill writes the audit-trail file — see the "Optional escalation" block at the bottom of the instructions. </background_information>
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.
- 3d ago First seen · 257 lines · 309 tokens per session scan B eda772621e89
ad-review is a skill published in the GitHub repository CorridorTech/PoseCap (190 stars, last pushed 10d ago), licensed Apache-2.0. It adds 309 tokens to every session and 4,262 once invoked, about $0.0015 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). 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.
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.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
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…