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.
git clone --depth 1 https://github.com/hgahlot/claude-flowWrote 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/commands/hgahlot/claude-flow/flow)<a href="https://agentmods.dev/commands/hgahlot/claude-flow/flow"><img src="https://agentmods.dev/badge/commands/hgahlot/claude-flow/flow/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/hgahlot/claude-flow/flow"><img src="https://agentmods.dev/badge/commands/hgahlot/claude-flow/flow.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00000 | $0.03509 |
| Opus 5.5 | $0.00000 | $0.01404 |
| Sonnet 5.5 | $0.00000 | $0.00702 |
| Haiku 4.5 | $0.00000 | $0.00351 |
Grade C, and why
flow scanned grade C with 1 finding 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 2mo 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
> PreToolUse hook: blocks rm -rf, DROP TABLE, force push automatically. How it starts
The opening of the file, as written. The whole thing — 547 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the unified development flow guide for this project. You are the ONLY command the user needs to remember. Everything — GSD, gstack, Superpowers, all of it — routes through you.
Your job: read what the user wants to do, find the right command, and present it clearly. Never say "use GSD" or "use gstack" — just say "run /command".
How to respond
- Read
STATE.mdto understand current project state and phase. - If the user passed a stage argument (e.g.
/flow build,/flow ship), jump directly to that section. - If no argument, check STATE.md and show the logical next step.
- If the user described a situation in natural language, find it in the routing table below and show the matching section.
- Always end with: "Ready to run this? I can kick it off for you."
Show each command like this:
/command-name
What it does in one sentence. Then 2–3 bullet points of what actually happens.
THE PIPELINE
Always show this header so the user knows where they are:
THINK → DESIGN → INIT → [ PLAN → BUILD → TEST → REVIEW → ACCEPT ] → SHIP → DEPLOY → MONITOR
└────────────── repeat per feature ───────────────┘
STAGE: THINK
Starting something new and want to validate the idea first
/ce:ideate
Discover high-impact improvements through divergent ideation and adversarial filtering.
- Generates grounded ideas based on your actual codebase
- Critically evaluates each idea before presenting
- Use when you need inspiration for what to build next
/office-hours
YC-style product forcing questions before writing a line of code.
- Asks 6 forcing questions, researches competitors, surfaces riskiest assumptions
- Produces a design doc with problem/solution/differentiation
- Use for pure product/business validation
STAGE: DESIGN
Need to lock in the visual or system design before building
/design-consultation
Builds a complete DESIGN.md + HTML preview.
- Pattern database activates automatically: 67 styles, 96 palettes, stack-specific patterns
- For a scoped UI phase (not full product design), use
/gsd:ui-phaseinstead
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.
- 2mo ago First seen · 547 lines · 0 tokens per session scan C afe7a6d4a5fa
flow is a command published in the GitHub repository hgahlot/claude-flow (55 stars, last pushed 7mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,509 tokens. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
flow compared with commands from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| flowhgahlot/claude-flow | Command | 55 | 7mo ago | MIT | C | 0 | Claude Code |
| cost-optimizewshobson/agents | Command | 42k | yesterday | MIT | A | 26 | Claude Code |
| deploybutterbase-ai/butterbase-skills | Command | 535 | 6d ago | MIT | A | 20 | Claude Code |
| envvercel/vercel-plugin | Command | 326 | yesterday | none | A | 35 | Claude Code |
| firebase-publishPierry/harness-kit | Command | 4 | 1mo ago | MIT | A | 20 | Claude Code |
| scanprajapatimehul/claude-aws-cost-saver | Command | 24 | 4mo ago | MIT | A | 6 | Claude Code |
| migrationdatabayt/hogwarts | Command | 18 | 3d ago | none | A | 4 | Claude Code |