Install
$ agentstack add skill-0xrafasec-ai-workflow-rfc ✓ 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
Create a Request for Comments. Argument: $ARGUMENTS
Context
RFCs are for significant changes that need team input before implementation — new systems, major refactors, breaking changes, process changes. Heavier than an ADR, lighter than a full spec. The goal is to get feedback, not to be exhaustive.
Context Gathering
- Check
docs/rfc/for existing RFCs — determine the next number. If none exist, start at0001. - Read recent RFCs (last 2-3) to match the project's style.
- Read
docs/ARCHITECTURE.mdanddocs/PRD.mdif they exist — the RFC should reference existing design, not repeat it.
Interview
Use AskUserQuestion to understand the proposal deeply. Push back on vague motivation — "why now?" and "what happens if we don't do this?"
- Proposal — What are you proposing? What's the elevator pitch?
- Motivation — Why is this needed? What's broken, missing, or changing? What happens if we do nothing?
- Scope — What does this change? What does it NOT change? Where are the boundaries?
- Design — How would this work at a high level? What are the key technical decisions?
- Alternatives — What other approaches were considered? Why not those?
- Migration — If this changes existing behavior, how do we get from here to there? Is it backwards-compatible?
- Risks — What could go wrong? What are the unknowns? What needs prototyping?
- Open questions — What do you want feedback on specifically? What are you least sure about?
Write
Write to docs/rfc/NNNN-.md:
# RFC-NNNN: [Title]
**Status:** Draft | In Review | Accepted | Rejected | Withdrawn
**Author:** [who]
**Date:** [date]
**Review deadline:** [date, if applicable]
## Summary
[2-3 sentence elevator pitch. What is this and why should someone care?]
## Motivation
[Why is this needed? What problem does it solve? What happens if we don't do this?]
## Proposal
[Detailed description of the proposed change. Include diagrams (Mermaid) where they help. This should be concrete enough for someone to evaluate but not a full implementation spec.]
### Key Design Decisions
[Call out the important choices and why you made them.]
## Alternatives Considered
### [Alternative 1]
[Description, why it was rejected]
### [Alternative 2]
[Description, why it was rejected]
## Migration Plan
[If this changes existing behavior: how do we transition? Is it backwards-compatible? What's the rollback plan?]
[If greenfield: skip this section]
## Risks and Open Questions
| Item | Type | Status |
|------|------|--------|
| [concern] | Risk / Question | Open / Resolved: [answer] |
## Feedback Requested
[What specifically do you want reviewers to focus on? What are you least sure about?]
## References
- [Links to related docs, prior art, external resources]
After Writing
- Present the RFC to the user for review.
- Suggest: "Share this with the team for feedback. Once accepted, create feature specs with
/specfor the implementation work."
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: 0xrafasec
- Source: 0xrafasec/ai-workflow
- 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.