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-guidelinesnpx skills add CorridorTech/PoseCap --skill ad-guidelinesgit 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 | $0.00214 | $0.02066 |
| Opus 5 | $0.00107 | $0.01033 |
| Sonnet 5 | $0.00043 | $0.00413 |
| Haiku 4.5 | $0.00021 | $0.00207 |
Grade A, and why
ad-guidelines 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 — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
<background_information>
Layer 1 Constitution trinity member. Lazy lifecycle owner of GUIDELINES.md at the repo root. Companion to WORKFLOW.md (universal philosophy, kit-shipped) and AGENTS.md (distilled non-negotiable rules read every session).
GUIDELINES.md is the full reference; AGENTS.md is the distilled summary. Each AGENTS.md section that has detail points to the corresponding GUIDELINES.md section. The two never duplicate — ad-drift flags duplication as drift.
Skill is excluded from poc profile. Universal at solo / team / mature.
Codex auto-trigger on description keywords is less mature than Claude Code's. If auto-invocation does not fire when the user mentions engineering guidelines, code standards, SOLID, Object Calisthenics, testing strategy, or security policy, invoke this skill manually. </background_information>
Route elsewhere when:
- Scope is system structure →
ad-architecture. - Scope is product →
ad-prd. - Scope is vocabulary →
ad-domain. - Scope is one binding decision →
ad-adr. - Scope is wiring the gates →
ad-hooks.
Step 1 — codebase-first scan. Before any preference question, detect:
Language and toolchain:
package.json→ JS/TS; read engines, scripts, deps, devDeps.Cargo.toml→ Rust; read edition, deps, dev-dependencies.pyproject.toml/setup.cfg/requirements.txt→ Python.CMakeLists.txt/CMakePresets.json/vcpkg.json→ C/C++.go.mod→ Go.Gemfile,pom.xml,build.gradle,composer.jsonfor other stacks.
Test framework: jest/vitest/playwright/mocha configs, pytest, cargo [dev-dependencies], catch2/gtest in CMake, _test.go files.
Lint and format: .eslintrc.*, .prettierrc.*, .rustfmt.toml, clippy.toml, .ruff.toml, mypy.ini, .clang-format, .clang-tidy, .golangci.yml.
Hooks and CI: .husky/, lefthook.yml, .pre-commit-config.yaml, .githooks/, .github/workflows/, .gitlab-ci.yml, .circleci/.
Existing standards:
AGENTS.md## Code Styleand## Architectural Principles— extract into GUIDELINES, replace with pointers.ARCHITECTURE.md## Source Treeand## Dependency Rules— informs Clean Architecture §1.1.doc/adr/— binding decisions about error handling, naming, DI — carry forward.CONTEXT.md— domain vocabulary the guidelines must respect.
Canonical examples: for brownfield projects, identify candidate source files that future agents should imitate. Prefer one boundary example, one core/domain function, and one test. Record paths only, never pasted snippets. If no representative code exists, omit the section until the project has examples worth copying.
Profile: read .claude/agentic-state.json / .agents/agentic-state.json. Profile shapes strictness defaults (mature → strict Object Calisthenics by default; solo → loose).
Only after the scan produces no answer does the skill ask. Asking about something the repo already states wastes the user's attention.
Step 2 — pre-fill the template. Open templates/guidelines.md. Fill detected fields before any interview:
- §2.1 naming conventions table per language idiom.
- §2.2 error handling per language idiom.
- §2.5 canonical examples table, when representative code exists: boundary code, core/domain logic, and tests. Confirm the picks with the user before writing; do not declare weak code canonical.
- §6.1 toolchain + version + source-of-truth config file.
- §6.2 dependency manager from detected manifest.
- §7 static-analysis tools detected.
- §8 quality gates from hooks scan; mark
<not yet wired — invoke /ad-hooks>when absent. - §9.2 unit-test framework detected.
- §9.6 tag taxonomy kit defaults.
- §10 git workflow kit pattern (Conventional Commits, DCO sign-off via
ad-commit). - §11.1 document scope table kit-standard.
- §12 security boundaries from scan.
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 · 120 lines · 214 tokens per session scan A 245a15622eee
ad-guidelines is a skill published in the GitHub repository CorridorTech/PoseCap (190 stars, last pushed 10d ago), licensed Apache-2.0. It adds 214 tokens to every session and 2,066 once invoked, about $0.0011 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.
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…