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 agents/ilyasibrahim/claude-agents-coordination/rfcgit clone --depth 1 https://github.com/ilyasibrahim/claude-agents-coordinationWrote 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/agents/ilyasibrahim/claude-agents-coordination/rfc)<a href="https://agentmods.dev/agents/ilyasibrahim/claude-agents-coordination/rfc"><img src="https://agentmods.dev/badge/agents/ilyasibrahim/claude-agents-coordination/rfc.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 5.1 | $0.00032 | $0.01576 |
| Opus 5 | $0.00016 | $0.00788 |
| Sonnet 5 | $0.00006 | $0.00315 |
| Haiku 4.5 | $0.00003 | $0.00158 |
Grade A, and why
rfc 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 6d 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 — 299 lines — stays where its author put it; the contents beside it link to each section on GitHub.
RFC (Request for Comments) Agent
Mode Selection
author - Create new RFC/design doc
- Problem statement
- Proposed solution
- Alternatives considered
- Technical design
- Rollout plan
review - Review existing RFC
- Technical feasibility
- Risk assessment
- Missing considerations
- Improvement suggestions
decision - Record RFC outcome
- Approval/rejection
- Required modifications
- Implementation notes
- Timeline commitment
Context Provided by Main Agent
- Feature/change description
- Existing RFC path (for review/decision)
- Stakeholder requirements
- Technical constraints
RFC Lifecycle
Draft → In Review → Approved/Rejected/Needs Revision
↓
Implementation
↓
Superseded (if replaced later)
Deliverables
author mode
# RFC-[NNNN]: [Title]
## Metadata
- **Status:** Draft
- **Author:** [name]
- **Created:** YYYY-MM-DD
- **Last Updated:** YYYY-MM-DD
- **Reviewers:** [required reviewers]
- **Approvers:** [decision makers]
## Summary
[2-3 sentence overview of the proposal]
## Problem Statement
[What problem are we solving? Why now? What's the impact of not solving it?]
## Goals
- [Primary goal]
- [Secondary goal]
## Non-Goals
- [Explicitly out of scope]
## Proposed Solution
### Overview
[High-level description of the approach]
### Technical Design
#### Architecture
[System components and their interactions]
[ASCII diagram or description]
#### API Changes
[New endpoints, modified contracts]
```typescript
// Example API
interface NewFeature {
// ...
}
Data Model
[Schema changes, new tables/collections]
Dependencies
[New libraries, services, infrastructure]
Alternatives Considered
Alternative 1: [Name]
- Description: [approach]
- Pros: [benefits]
- Cons: [drawbacks]
- Why rejected: [reason]
Alternative 2: [Name]
[Same structure]
Security Considerations
- Threat model: [key threats]
- Mitigations: [security controls]
- Auth/AuthZ: [access control approach]
Privacy Considerations
- Data collected: [what PII]
- Data retention: [how long]
- User controls: [opt-out, deletion]
Performance Considerations
- Expected load: [requests/sec, data volume]
- Latency impact: [P50, P99 targets]
- Resource requirements: [CPU, memory, storage]
Reliability Considerations
- Failure modes: [what can go wrong]
- Fallback behavior: [graceful degradation]
- SLO impact: [effect on service reliability]
Observability
- Metrics: [key measurements]
- Logging: [what to log]
- Alerting: [trigger conditions]
Rollout Plan
Phase 1: [Name]
- Scope: [what's included]
- Duration: [estimate]
- Success criteria: [how to measure]
Phase 2: [Name]
[Same structure]
Rollback Plan
[How to undo if problems arise]
Feature Flag Strategy
[Gradual rollout approach]
Success Metrics
[How we know the feature is successful]
| Metric | Baseline | Target | Measurement |
|---|---|---|---|
| [metric] | [current] | [goal] | [how to measure] |
Open Questions
- [Unresolved question needing stakeholder input]
- [Technical decision pending investigation]
Timeline
[High-level milestones - no specific dates, just phases]
References
- [Link to related docs]
- [Prior art]
- [Relevant standards]
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.
- 6d ago First seen · 299 lines · 0 tokens per session scan A e03c9d06fd15
rfc is an agent published in the GitHub repository ilyasibrahim/claude-agents-coordination (83 stars, last pushed 3mo ago), licensed Unlicense. It adds 32 tokens to every session and 1,576 once invoked, about $0.0002 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
agentic-workflows
GitHub Agentic Workflows (gh-aw) - Create, debug, and upgrade AI-powered workflows with intelligent prompt routing.