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/gmickel/flow-next/flow-next-capturenpx skills add gmickel/flow-next --skill flow-next-capturegit 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/skills/gmickel/flow-next/flow-next-capture)<a href="https://agentmods.dev/skills/gmickel/flow-next/flow-next-capture"><img src="https://agentmods.dev/badge/skills/gmickel/flow-next/flow-next-capture.svg" alt="Measured on agentmods" 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 | $0.00030 | $0.03370 |
| Opus 5 | $0.00015 | $0.01685 |
| Sonnet 5 | $0.00006 | $0.00674 |
| Haiku 4.5 | $0.00003 | $0.00337 |
Grade A, and why
flow-next-capture 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.
How it starts
The opening of the file, as written. The whole thing — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/flow-next:capture — agent-native conversation → spec
A free-form discussion (or a /flow-next:prospect survivor) frequently produces enough material for a complete spec, but stops short of the formal flowctl spec create + spec set-plan heredoc documented in CLAUDE.md. Without an explicit synthesis step, that context decays — the next session loses the conversation, the spec never lands, and the user re-explains the same idea to /flow-next:plan.
Ask the user via plain text. Render the options below as a numbered list 1. … N., followed by a final option N+1. Other — type your own answer. Print the question, then the numbered list, then stop and wait for the user's next message before continuing. Parse the reply as: a bare number 1–N+1 → that option; the literal text of an option label → that option; free text after Other → custom answer.
This skill IS the synthesis. The host agent (Claude Code / Codex / Droid) extracts the recent user turns, drafts a CLAUDE.md-shaped spec with per-line source tags ([user] / [paraphrase] / [inferred] / [strategy:<track>]), prints the full draft as ordinary markdown then issues a short approval ask (print-then-ask — never embed multi-paragraph drafts in plain-text numbered prompt bodies), and only then writes the spec via existing flowctl plumbing. There is no Python synthesizer, no codex / copilot subprocess, no fast-model classifier. The host agent is already an LLM and does the work directly.
flowctl provides thin spec plumbing (spec create, spec set-plan, optional spec set-branch, memory search for duplicate detection) plus the chart handoff callback (chart link-spec) after a successful chart-briefing capture. Capture never writes chart files and never mutates a chart's ready flag; chart never writes .flow/specs.
Routing boundary (fn-135 / guide matrix)
Clear meaningful ideas and finished chart briefings route here - to capture (or direct spec authoring). Capture does not manufacture a chart for clear work. When intent and boundaries are already stateable, skip chart (signal absent). After a structured brief lands, narrow or skip interview only once read-back proves no material gaps - never pre-skip interview on hope. Unsure: /flow-next:guide.
What ships with it
16 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- agents/openai.yaml 231 B
- phases.md 11 KB
- references/autofix-mode.md 4.4 KB
- references/chart-briefing.md 10 KB
- references/codebase-verification.md 2.1 KB
- references/duplicate-branch.md 3.6 KB
- references/glossary-terms.md 4.8 KB
- references/html-lens.md 4.6 KB
- references/manual-smoke.md 4.1 KB
- references/mark-ready.md 6.2 KB
- references/must-ask-cases.md 5.6 KB
- references/rewrite-mode.md 6.0 KB
- references/split-proposal.md 8.7 KB
- references/strategy-alignment.md 7.8 KB
- references/tracker-integration.md 7.1 KB
- workflow.md 60 KB
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 Changed · +16 lines a1204fdd1d45
- 5d ago Changed · +1 lines f28d745a5c3e
- 6d ago First seen · 152 lines · 30 tokens per session scan A 81030c695d10
flow-next-capture is a skill published in the GitHub repository gmickel/flow-next (691 stars, last pushed today), licensed MIT. It adds 30 tokens to every session and 3,370 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 2026-08-30.
Other skills, from other repositories
exec
Execute plan tasks sequentially using subagents. Use when user says 'exec', 'execute plan', 'run plan', or wants to implement a plan file task by task with isolated subagents.
pr
Comprehensive PR/issue review - analyzes architecture, tests, identifies unrelated changes mixed in, drafts review comment or issue comment. Use when user asks to review a PR, check a PR, look at PR changes, or comment on an issue.
project-execution
Executes implementation plans with progress tracking, checkpoint validation, and quality gates. Use after planning is complete and tasks are ready to implement.
backlog
Read, work, and maintain a Git repo's deferred-work items in docs/backlog/, one file per item. Use when the user says "backlog", "check backlog", "what's on my backlog", "work the backlog", "address the backlog", "add to backlog", "clean up backlog", or when a review or task produced items that are real but not being…
ask-codex
Consult OpenAI Codex for investigation, debugging, or code review. Use when user explicitly asks to "ask codex", "check with codex", "codex review", or as a last resort when stuck after 4+ failed attempts at debugging, investigation, or bug fix and completely out of ideas. Codex is slow (2-5 min), so only escalate…
new
Use when user asks to create a release, cut a release, or publish a version. Auto-detects GitHub vs GitLab vs Gitea, calculates semantic version, generates release notes from PRs/MRs or commits, shows preview for confirmation before publishing.