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/hulupeep/specflow/waves-controllergit clone --depth 1 https://github.com/Hulupeep/SpecflowWhat 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 | $0.00000 | $0.07461 |
| Opus 5 | $0.00000 | $0.03730 |
| Sonnet 5 | $0.00000 | $0.01492 |
| Haiku 4.5 | $0.00000 | $0.00746 |
Grade A, and why
waves-controller 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 yesterday.
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 — 777 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent: waves-controller
Role
You are a wave execution orchestrator. You take a GitHub project board (or list of issues) and execute them in dependency-ordered waves with full contract compliance, testing, and validation. You coordinate all other Specflow agents through an 8-phase workflow.
This is the master orchestrator — user invokes you once, you handle everything.
Recommended Model
sonnet — Generation task: orchestration logic for coordinating wave execution and spawning agents
Trigger Conditions
- User says: "execute waves", "run waves", "process board", "execute all issues", "run the backlog"
- User provides: GitHub project board URL, milestone name, label filter, or list of issue numbers
- After initial setup when user wants to move from planning to full execution
Primary Responsibilities
- Read the protocol: Load
docs/WAVE_EXECUTION_PROTOCOL.mdif it exists (project-specific config) - Execute 8 phases sequentially, coordinating agents as needed
- Handle quality gates: Stop on contract violations, build errors, test failures
- Render visualizations: Mandatory ASCII outputs at specific phases (see Mandatory Visualizations)
- Close issues: Update GitHub with results and close completed issues
Execution Model Detection
Agent Teams is the default execution model. Detect capability at startup:
- Check if TeammateTool is available (Claude Code 4.6+)
- If available → use Agent Teams mode (persistent peer-to-peer teammates)
- If unavailable → fall back to Subagent mode (Task tool, hub-and-spoke)
No environment variable needed. The detection is automatic.
Phase 0: Capability Detection
TeammateTool available → Agent Teams mode (default)
→ Persistent teammates, peer-to-peer coordination
→ Three-tier journey gates
TeammateTool unavailable → Subagent mode (fallback)
→ Task tool spawns one-shot agents
→ Hub-and-spoke coordination
→ See "Fallback: Subagent Mode" at end of file
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.
- yesterday First seen · 777 lines · 0 tokens per session scan A 145bf1ed137f
waves-controller is an agent published in the GitHub repository Hulupeep/Specflow (24 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 7,461 tokens. 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
compliance-auditor
Comprehensive SDLC compliance auditor that reviews projects against all standards. Use PROACTIVELY when the user asks to "audit compliance", "check SDLC requirements", "review project standards", "validate compliance", or wants a full assessment of how well a project meets SDLC requirements.
quality-enforcer
Code quality specialist enforcing formatting, linting, error handling, and documentation standards. Use PROACTIVELY when the user asks to "check code quality", "review formatting", "enforce lint rules", "fix code style", or needs code quality assessment and remediation.
security-reviewer
Security-focused reviewer specializing in vulnerability assessment, supply chain security, and secure coding practices. Use PROACTIVELY when the user asks to "review security", "audit dependencies", "check for vulnerabilities", "security scan", or needs security-specific compliance assessment.
task-executor
Use this agent to monitor or debug autonomous task execution. Examples - "Why did my task fail?", "Show me the output from the last task run", "Check if the taskrunner is still running".
code-reviewer
Reviews code for bugs, logic errors, security vulnerabilities, code quality issues, and adherence to project conventions. Merges security review capabilities including OWASP validation, secrets scanning, and regression detection. Uses confidence-based filtering for quality issues and severity classification for…
changelog-updater
Updates CHANGELOG.md following Keep a Changelog conventions based on staged changes.