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/uninstall)<a href="https://agentmods.dev/commands/gmickel/flow-next/uninstall"><img src="https://agentmods.dev/badge/commands/gmickel/flow-next/uninstall/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/uninstall"><img src="https://agentmods.dev/badge/commands/gmickel/flow-next/uninstall.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 | $0.00009 | $0.00795 |
| Opus 5.5 | $0.00004 | $0.00318 |
| Sonnet 5.5 | $0.00002 | $0.00159 |
| Haiku 4.5 | $0.00001 | $0.00080 |
Grade C, and why
uninstall 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 23d 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.
rm -rf .flow/bin .flow/templates .flow/usage.md How it starts
The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Flow-Next Uninstall
Use AskUserQuestion to confirm:
Question 1: "Remove flow-next from this project?"
- "Yes, uninstall"
- "Cancel"
If cancel → stop.
Question 2: "Keep your .flow/ tasks and specs?"
- "Yes, keep tasks" → partial uninstall
- "No, remove everything" → full uninstall
Generate removal instructions
Based on answers, generate the appropriate commands and print them for the user to run manually.
If keeping tasks:
Setup copies nothing into .flow/, so uninstall there is marker removal: strip the <!-- BEGIN FLOW-NEXT -->...<!-- END FLOW-NEXT --> block from CLAUDE.md / AGENTS.md (the "Clean up docs" section below does that) and remove the setup_version / setup_mode stamps from .flow/meta.json.
Legacy cleanup — only when those paths actually exist (repos set up before copy-less installs). Print this for the user to run manually; omit it entirely when none exist:
To complete uninstall, run these commands manually:
rm -rf .flow/bin .flow/templates .flow/usage.md
If removing everything:
To complete uninstall, run these commands manually:
rm -rf .flow
Always check for Codex agent configs and add if any exist. On Codex, setup copies flow-next's agent configs into .codex/agents/; each starts with # Auto-generated by sync-codex.sh. Remove only those, so user-authored agents stay:
if grep -lq '^# Auto-generated by sync-codex.sh' .codex/agents/*.toml 2>/dev/null; then
echo "grep -l '^# Auto-generated by sync-codex.sh' .codex/agents/*.toml | xargs rm -f"
fi
Clean up docs (AI can do this)
For CLAUDE.md and AGENTS.md: if file exists, remove everything between <!-- BEGIN FLOW-NEXT --> and <!-- END FLOW-NEXT --> (inclusive). This is safe for the AI to execute.
Also remove the optional model-routing scaffold block (written by /flow-next:setup) from the same files. It is a second, independent marker pair: <!-- flow-next:model-routing:start --> … <!-- flow-next:model-routing:end -->. Apply the deterministic damaged-marker algorithm — line-based, never parsing the fenced content (the block is an example whose routing lines are all HTML comments):
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.
- 23d ago Changed · -25 lines 5515bd7d85d3
- 29d ago Changed · +8 lines d6778eaca447
- 1mo ago First seen · 91 lines · 9 tokens per session scan C febef9f36864
uninstall is a command published in the GitHub repository gmickel/flow-next (711 stars, last pushed yesterday), licensed MIT. It adds 9 tokens to every session and 795 once invoked, about $0.0000 per session on Opus 5.5. 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 2026-09-03.
Other commands, from other repositories
speckit.checklist
Generate a custom checklist for the current feature based on user requirements.
speckit.clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
speckit.specify
Create or update the feature specification from a natural language feature description.
speckit.analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
speckit.implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
speckit.tasks
Generate an actionable, dependency-ordered tasks.md for the feature based on available design artifacts.