Install
$ agentstack add skill-andregusman-raiz-a-gusman-claude-ag-construir-validado ✓ 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.
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
ag-construir-validado — Builder/Validator Pattern
Implements the builder/validator pattern where implementation and review happen concurrently instead of sequentially.
Invocation
Use the Agent tool with:
subagent_type:general-purposemode:autoprompt: Compose from template below
Prompt Template
Projeto: [CWD]
Scope: [from arguments]
## Pattern: Builder + Validator Concurrent
1. Read task_plan.md to understand what needs to be built
2. Spawn TWO agents in parallel:
**Builder (ag-implementar-codigo)**:
- Agent tool with subagent_type: ag-implementar-codigo
- isolation: worktree
- Implements all items from task_plan.md
- Commits incrementally every 5 actions
**Validator (ag-revisar-codigo)**:
- Agent tool with subagent_type: ag-revisar-codigo
- run_in_background: true
- Reviews code as it's committed
- Reports issues found
3. During build: Builder uses LSP tool (hover/documentSymbol) for instant type validation on modified files — avoids spawning tsc during iterative work
4. After both complete:
- Read validator output
- If issues found: fix them
- Run quality gates: tsc full (`bun run typecheck`) + lint + test (only here, not during build)
- Report final status
Inter-Agent Communication
- Builder uses SendMessage to notify coordinator at key milestones:
- Module complete, blocker found, self-check result
- Validator uses SendMessage to report issues found during review
- Coordinator reads messages and decides: continue, fix, or escalate
Important
- Builder and validator run CONCURRENTLY — this is the key innovation
- Validator reviews code as it appears, not after all code is written
- This reduces cycle time vs sequential build→review
- allowed-tools for coordinator MUST include SendMessage
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: andregusman-raiz
- Source: andregusman-raiz/a-gusman-claude
- 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.