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/compozy/skeeper/cy-spec-preflightnpx skills add compozy/skeeper --skill cy-spec-preflightgit clone --depth 1 https://github.com/compozy/skeeperWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/compozy/skeeper/cy-spec-preflight)<a href="https://agentmods.dev/skills/compozy/skeeper/cy-spec-preflight"><img src="https://agentmods.dev/badge/skills/compozy/skeeper/cy-spec-preflight.svg" alt="Measured on agentmods" height="20"></a>What 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 | $0.00120 | $0.01764 |
| Opus 5 | $0.00060 | $0.00882 |
| Sonnet 5 | $0.00024 | $0.00353 |
| Haiku 4.5 | $0.00012 | $0.00176 |
Grade A, and why
cy-spec-preflight 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 4d 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 — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Spec Preflight
Authors of AGH PRDs, TechSpecs, and _tasks.md repeatedly produce drafts that miss project-specific directives — frameworks named in PRDs, prose-only TechSpecs, "fraco" test coverage. This skill loads project memory before handing off to cy-create-prd, cy-create-techspec, or cy-create-tasks, then runs the relevant post-draft checks before approval.
Required Inputs
- phase (optional): one of
prd,techspec,tasks, ortask-body. When omitted, infer from the activecy-create-*skill or from the artifact path (_prd.md,_techspec.md,_tasks.md,task_NN.md).
Procedures
Step 1: Load Project Memory
- Read
docs/_memory/spec-authoring-playbook.mdin full. - Read
docs/_memory/standing_directives.md(SD-001..SD-011). - Read
docs/_memory/glossary.md(vocabulary discipline —capabilityvsrecipe, AGH is/is-not). - Read the matching lessons by phase. Read
references/phase-lessons.mdfor the phase → lesson mapping. - Read
CLAUDE.mdAuthoring Posture, Architecture Principles, Autonomy Contracts, Security Invariants sections.
Step 2: Load Active Project Context
- Resolve the active task slug: the
.compozy/tasks/<slug>/directory the artifact targets. - If a
_techspec.mdexists at the slug, read it before authoring tasks. - If
adrs/*.mdexist, read every one before authoring techspec/tasks. - If
analysis/*.mdexist (e.g., fromcy-research-competitors), read before authoring techspec. - If a prior phase artifact exists (PRD before TechSpec, TechSpec before Tasks), read it.
Step 3: Apply Phase-Specific Checks
Phase-specific checks below. Run only the relevant block. Use the "before authoring" checks before the inner skill writes a draft, and the "after draft" checks before user approval.
Phase: prd
- Read
references/prd-checks.md. - Before authoring, confirm the active idea is framed as WHAT/WHY/WHO and not implementation detail.
- After the draft is produced, run
python3 scripts/check-prd-implementation-leak.py <prd_path>to surface framework/storage/error-code/file-format names. Strip every match unless the PRD is about the named technology. - Confirm the PRD lists explicit Goals, Non-Goals, Success Metrics, and Open Questions using the canonical
cy-create-prdtemplate. - Confirm the PRD states the agent/operator manageability outcome and extension ecosystem expectation without naming implementation details.
- Do not invoke
cy-spec-peer-reviewfor PRDs. Peer review is TechSpec-only and user-directed.
What ships with it
8 files 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.
- references/phase-lessons.md 1.6 KB
- references/prd-checks.md 2.0 KB
- references/tasks-checks.md 3.2 KB
- references/techspec-six-markers.md 4.0 KB
- scripts/__pycache__/check-prd-implementation-leak.cpython-314.pyc 5.0 KB
- scripts/__pycache__/check-techspec-markers.cpython-314.pyc 6.9 KB
- scripts/check-prd-implementation-leak.py 3.0 KB runs code
- scripts/check-techspec-markers.py 4.0 KB runs code
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.
- 4d ago First seen · 110 lines · 120 tokens per session scan A 74f55d211f7a
cy-spec-preflight is a skill published in the GitHub repository compozy/skeeper (85 stars, last pushed 3mo ago), licensed MIT. It adds 120 tokens to every session and 1,764 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
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…