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/gmickel/flow-nextWrote 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/gmickel/flow-next/flow)<a href="https://agentmods.dev/commands/gmickel/flow-next/flow"><img src="https://agentmods.dev/badge/commands/gmickel/flow-next/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/gmickel/flow-next/flow"><img src="https://agentmods.dev/badge/commands/gmickel/flow-next/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 | $0.00086 | $0.00385 |
| Opus 5.5 | $0.00034 | $0.00154 |
| Sonnet 5.5 | $0.00017 | $0.00077 |
| Haiku 4.5 | $0.00009 | $0.00038 |
Grade A, and why
flow 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 10d 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
IMPORTANT: This command MUST invoke the skill flow-next-flow
The ONLY purpose of this command is to call the flow-next-flow skill. You MUST use that skill now.
Arguments: $ARGUMENTS
Pass the arguments to the skill verbatim. The skill routes from its shared routing reference, dispatches the existing stage skills, re-evaluates after each hop, and stops at the next human decision. --explain prints the route and its reason with no .flow/ write and no dispatch. --auto runs the same route unattended from the ready flag, hop after hop to a terminal (--tick for exactly one hop), and ends with one PILOT_VERDICT line. --until=merge independently selects gated landing through the existing land stage for the selected spec and PR. Default unattended flow stops before merge; plain attended flow offers landing for an existing PR and asks once unless current scoped authorization already exists. The skill's tail reference owns consent, continuation, and recovery.
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.
- 10d ago Changed 4a1cb39b9506
- 19d ago Changed · +1 lines 3e8bee1eb58f
- 1mo ago Changed · +31 tokens per session 43816a856857
- 1mo ago First seen · 14 lines · 55 tokens per session scan A 05f2e081920b
flow is a command published in the GitHub repository gmickel/flow-next (710 stars, last pushed today), licensed MIT. It adds 86 tokens to every session and 385 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-09-12.
Other commands, from other repositories
speckit.tasks
Generate an actionable, dependency-ordered tasks.md for the feature based on available design artifacts.
speckit.taskstoissues
Convert existing tasks into actionable, dependency-ordered GitHub issues for the feature based on available design artifacts.
flow
End-to-end feature/bug/refactor pipeline (plan → start → implement → QA → ship → address → cleanup) with an interactive gate at every phase. Resumable via /orc:resume. --jira links a ticket. Workspace-aware.
OPSX: Archive
Archive a completed change in the experimental workflow.
OPSX: Apply
Implement tasks from an OpenSpec change (Experimental).
speckit.specify
Create or update the feature specification from a natural language feature description.