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 skills/billbuchanan-code/claude-code-power-setup/flow.orchestratenpx skills add billbuchanan-code/claude-code-power-setup --skill flow.orchestrategit clone --depth 1 https://github.com/billbuchanan-code/claude-code-power-setupWhat 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 | $0.00025 | $0.05429 |
| Opus 5 | $0.00013 | $0.02714 |
| Sonnet 5 | $0.00005 | $0.01086 |
| Haiku 4.5 | $0.00003 | $0.00543 |
Grade A, and why
flow.orchestrate 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 — 672 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CRITICAL RULES
YOU MUST FOLLOW THESE RULES WITHOUT EXCEPTION:
- NEVER edit
.specflow/orchestration-state.jsondirectly - Usespecflow state set - NEVER edit
tasks.mdto mark tasks complete - Usespecflow mark T### - NEVER skip steps - Execute in order: design → analyze → implement → verify
- ALWAYS verify step completion before advancing to next step
- ALWAYS use the SpecFlow CLI for all state and task operations
- NEVER STOP between steps - This is a CONTINUOUS workflow. After completing each step, immediately continue to the next step. Only stop at USER GATEs or when all steps are complete.
- Use
specflowdirectly, NOTnpx specflow- The CLI is installed at~/.claude/specflow-system/bin/specflow, not an npm package.
If you find yourself about to use the Edit tool on state files or tasks.md, STOP and use the CLI instead.
CONTINUOUS EXECUTION: Orchestration runs design → analyze → implement → verify in ONE session. Do not stop to ask "should I continue?" or report intermediate completion. Keep going until you reach a USER GATE or finish verify.
User Input
$ARGUMENTS
| Argument | Action |
|---|---|
(empty) or continue |
Resume from current state |
reset |
Clear state and restart current phase |
status |
Show status only, don't execute |
skip-to [step] |
Skip to step (design, analyze, implement, verify) |
Goal
Execute the complete SpecFlow development workflow with:
- State persistence - Survives conversation compaction
- Self-healing - Detects and recovers from inconsistencies
- Minimal user interaction - Only asks when truly necessary
- Auto-fix loop - Fixes ALL issues found during analyze until clean
Workflow Overview
| Step | Index | Command | Purpose | User Interaction |
|---|---|---|---|---|
| design | 0 | /flow.design |
Create all design artifacts | Progressive questions |
| analyze | 1 | /flow.analyze |
Cross-artifact consistency | Auto-fix loop |
| implement | 2 | /flow.implement |
Execute all tasks | Progress updates |
| verify | 3 | /flow.verify |
Verify completion | USER GATE if applicable |
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 · 672 lines · 25 tokens per session scan A 15995265e180
flow.orchestrate is a skill published in the GitHub repository billbuchanan-code/claude-code-power-setup (2 stars, last pushed 1mo ago), licensed MIT. It adds 25 tokens to every session and 5,429 once invoked, about $0.0001 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 skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.