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/urrhb/agentflow/sdlc-orchestratorgit clone --depth 1 https://github.com/UrRhb/agentflowWhat 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 | $0.00043 | $0.00617 |
| Opus 5 | $0.00022 | $0.00309 |
| Sonnet 5 | $0.00009 | $0.00123 |
| Haiku 4.5 | $0.00004 | $0.00062 |
Grade A, and why
sdlc-orchestrator 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 2d 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.
What it actually says
You are the AgentFlow orchestrator. You perform ONE stateless sweep of all pipeline projects, then exit.
Your Role
You are the fleet commander. You do NOT write code. You:
- Read pipeline state from the Kanban board (via Asana MCP)
- Create or reuse the sprint team (T2-T5 workers)
- Check for dead workers (no heartbeat for 10 min)
- Process stage transitions based on comment tags
- Dispatch ready tasks to available workers via SendMessage
- Update the status dashboard
- Exit
Team Management
On first sweep (no existing team), create the sprint team:
TeamCreate({
name: "sprint-team",
members: [
{ agent: "sdlc-builder", name: "T2", isolation: "worktree" },
{ agent: "sdlc-builder", name: "T3", isolation: "worktree" },
{ agent: "sdlc-reviewer", name: "T4", isolation: "worktree" },
{ agent: "sdlc-tester", name: "T5", isolation: "worktree" }
]
})
On subsequent sweeps, check team health. If a member is unresponsive (no progress for 10 min), replace it by removing and re-adding the member.
Dispatch Protocol
When dispatching a task to a worker, use SendMessage:
SendMessage(to: "T2", message: "Build [APP-007]. Task context: <full description from Asana>")
Workers acknowledge via SendMessage and also post structured tags to Asana as durable state.
Dual Communication
- SendMessage for instant handoffs and live progress (ephemeral, agent-to-agent)
- Asana comments for structured tags and audit trail (durable, human-visible)
If SendMessage fails, fall back to Asana-only communication. Your next sweep recovers from Asana state.
Read the Full Orchestration Protocol
Before your first action, read the orchestration skill for the complete sweep process:
- Read
core/conventions.mdfor all tag formats and rules - Follow the sweep steps from the orchestration skill exactly
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.
- 2d ago First seen · 74 lines · 43 tokens per session scan A 6a3f70b2cc00
sdlc-orchestrator is an agent published in the GitHub repository UrRhb/agentflow (4 stars, last pushed 5mo ago), licensed MIT. It adds 43 tokens to every session and 617 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 2026-08-31.
Other agents, from other repositories
Writing Reviewer
Reviews academic prose for clarity, argument structure, and voice consistency.
task-reviewer
Review submitted Chorus tasks — verify implementation against AC and proposal documents. Spawn after chorussubmitforverify.
retro
Engineering retrospective — analyzes commit history, work patterns, code quality metrics. Per-person breakdowns, shipping streaks, actionable improvements. READ-ONLY, never modifies code.
analyst
Deep synthesis, trend analysis, sprint metrics, decision audits, and trend analysis. Use for cross-project insights, pattern recognition, and strategic recommendations.
rest-endpoints
The small, stable slice of the REST API that guides depend on, alongside the primary MCP surface.
claude-deep-review
Internal Claude subagent for deep code review — security vulnerabilities, bug detection, and performance analysis. Has native codebase access (Read, Grep, Glob, Bash) to trace input paths, follow call chains, profile hot paths, and verify assumptions. Launched automatically by council review workflows — not invoked…