Project Design
Design phase for {PROJECT} — data model, module boundaries, API contract, access control, and any multi-tenancy/security design, before code is written. Called by project-orchestrator before implementation; also used directly when the user says "design {PROJECT}'s X module.
Install
$ agentstack add skill-cormff-claude-code-playbook-project-design ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Links to your public security report.[](https://agentstack.voostack.com/security/report/skill-cormff-claude-code-playbook-project-design) Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
{PROJECT} Design
Produces the design artifacts that [project-implement](../project-implement/SKILL.md) will build against, and records any durable architectural decision.
Produce
- Data model — entities, relationships, and any project-wide invariants (e.g. tenant scoping, required indexes).
- Module boundaries — what this module owns, what it exposes to (and consumes from) other modules.
- API contract — request/response shapes, or an OpenAPI-style spec if the project already uses one.
- Access control — who/what can do what.
- Cross-cutting concerns, if relevant — multi-tenancy isolation, security constraints.
Recording decisions
Any decision that would be expensive to silently reverse later (a schema choice, a boundary, a naming convention applied project-wide) goes into Decisions.md (see [project-orchestrator](../project-orchestrator/SKILL.md#workspace-fill-in-with-real-paths)) as a short ADR: context, decision, why, alternatives considered. Anything already locked there is a constraint on this design, not a fresh choice — flag it as the "genuinely critical decision" stop condition in the orchestrator if a real conflict comes up.
Output
A design note under the module's vault folder, structured so [project-implement](../project-implement/SKILL.md) can build directly from it without re-deriving decisions that were already made here.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: cormff
- Source: cormff/claude-code-playbook
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.