Install
$ agentstack add skill-bnet47-codexicon-architecture-review ✓ 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
Architecture review
Announce: "I'm using architecture-review to evaluate this decision and record its consequences."
1. Load decision context
Read relevant accepted ADRs, agent_docs/architecture.md, project constraints, and the code that establishes the current system. If an ADR already settles the question, surface it and determine whether new evidence justifies superseding it.
2. Research only unstable facts
For current libraries, platform capabilities, pricing, limits, or deprecations, use a read-only researcher and primary sources. Do not browse merely to validate general engineering principles.
3. Define decision drivers
State the decision, constraints, non-negotiable qualities, and observable signals that would make the choice fail. Evaluate two or three viable options against the drivers most relevant here, normally including:
- product and constraint fit;
- operational complexity and failure isolation;
- security and data ownership;
- reversibility and migration cost;
- delivery and ongoing cost;
- testability, observability, and agent/developer navigability.
Avoid false precision. Use qualitative ratings unless reliable measurements exist.
4. Recommend and obtain direction
Lead with the recommended option, its decisive reason, and its largest downside. Ask the user only when the choice changes product behavior, cost, or irreversible commitments beyond the authority already granted.
5. Record the ADR only when authorized
If the user asked only for advice, a comparison, or a review, return the recommendation without modifying the repository. Create or update architecture documents only when the user asked to record the decision, asked for implementation that includes the decision, or explicitly delegated repository changes.
Copy docs/adr-template.md to the next available agent_docs/decisions/ADR-NNN-[slug].md.
- Use
Status: Proposedwhen a required human decision is pending. - Use
Status: Acceptedwhen the user chose the option or explicitly delegated the decision. - Link any superseded ADR from the new record; do not rewrite the accepted historical decision.
- Update
agent_docs/architecture.mdwhen the accepted choice changes system shape.
Do not commit or push the ADR unless the user asks to ship.
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: bnet47
- Source: bnet47/codexicon
- License: MIT
- Homepage: https://bnet47.github.io/codexicon/repo-template-playbook.html
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.