Skip to main content
skill CX Codex

flow-next-features — Claude Code skill: feature map

flow-next-features is a Claude Code skill that creates or updates a user-facing feature map in .flow/features/. QA and drive can reuse its notes on how users reach each feature.

MIT ★ 730 updated 2026-10-29

Install into Claude Code · Plugin marketplace All methods and platforms ↓
/plugin marketplace add gmickel/flow-next
/plugin install flow-next@flow-next
Open on GitHub

What flow-next-features does

The skill inspects a repository and records what each user-facing feature does and how to reach it. If .flow/features/ is missing or initialization is requested, it tests routes with a live drive and writes an index plus a file for each verified feature. With an existing map, it audits and maintains the current entries.

For repositories with multiple surfaces, such as a web app and CLI, entries are grouped by surface. Reinitializing an existing map requires .flow/features/ to be clean in Git; otherwise the run stops with BLOCKED. The skill responds to /flow-next:features and feature-map requests. Autonomous drivers such as flow --auto must not dispatch it.

What it helps with

  • create a user-facing feature map for a repository
  • record the routes users take to reach features
  • audit and update an existing feature map
  • group web and CLI features by surface

Example prompts for the agent

  • Run /flow-next:features and create a feature map for this repository.
  • Maintain the feature map in .flow/features/.
  • Reinitialize the feature map.

How to install flow-next-features

1Plugin marketplace

/plugin marketplace add gmickel/flow-next
/plugin install flow-next@flow-next

This installs the whole flow-next plugin with all its skills

2Skills CLI (Vercel)

npx skills add gmickel/flow-next --skill flow-next-features -a claude-code

3Manually: put the files in place

~/.claude/skills/flow-next-features/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/flow-next-features/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about flow-next-features

How do I install flow-next-features in Claude Code?

Run these commands in order: /plugin marketplace add gmickel/flow-next, then /plugin install flow-next@flow-next.

What does flow-next-features do?

It creates a user-facing feature map in .flow/features/ or checks and updates an existing one. The map records how users reach each feature.

When does flow-next-features seed a map instead of maintaining it?

It seeds the map when .flow/features/ is absent or initialization is explicitly requested. If the directory exists and there is no init intent, it audits and maintains the existing map.

Source text

SKILL.md · MIT
---
name: flow-next-features
description: 'Seed or maintain the committed user-POV feature map at `.flow/features/` so QA and drive reuse how a user reaches each feature. Two state-resolved modes: no `.flow/features/` (or explicit init intent) seeds it; a present map maintains it. Triggers on /flow-next:features, "seed the feature map", "maintain the feature map", "feature map", "init features". Never dispatched by `flow --auto`, land, or any autonomous driver.'
user-invocable: false
allowed-tools: AskUserQuestion, Read, Bash, Grep, Glob, Write, Edit, Task
---

# /flow-next:features - compounding user-POV drive knowledge

A committed directory (`.flow/features/`, beside `.flow/memory/`) records, from the user's point of view, what each user-facing feature is, how a user reaches it, how an agent drives it, and which traps waste a verification run. QA and drive stop re-deriving navigation; work can reuse it to verify what it built.

Split that keeps existing contracts intact: **map = how a user gets there (compounds). Spec = what to prove this time. Live drive = proof.**

Seed-mode phases live in [seed.md](seed.md); read it only once mode detection resolves `MODE=seed`. Feature file shape: [references/feature-entry-contract.md](references/feature-entry-contract.md). Doctor + proof: [references/doctor-and-proof.md](references/doctor-and-proof.md). Maintain (when `MODE=maintain`) executes [maintain.md](maintain.md).

The skill validates the four-H2 shape itself. Its flowctl calls on the maintain path are `features status` (read-only: last-proven age and open drift notes), `memory list` for the `feature-map-drift` tag handoff, `memory mark-stale` to retire drift notes whose route proved, and `memory add` (overlap-judged fold) for bug filing.

This skill and work's feature-map update step (entries its own change altered, [feature-map-update.md](../flow-next-work/references/feature-map-update.md)) are the only map writers; every other stage reads the map and files drift notes ([references/feature-entry-contract.md](references/feature-entry-contract.md), "Writers and drift notes").

Read [working-rules.md](../../references/working-rules.md) first unless you already have this run; it holds for every step of this skill.

## Preamble

**CRITICAL: flowctl is BUNDLED - NOT installed globally.** `which flowctl` will fail (expected). Define once; subsequent blocks (here and in `maintain.md`) use `$FLOWCTL`:

```bash
FLOWCTL="${DROID_PLUGIN_ROOT:-${CLAUDE_PLUGIN_ROOT}}/scripts/flowctl"
[ -x "$FLOWCTL" ] || FLOWCTL="<plugin-root>/scripts/flowctl"   # <plugin-root> = the directory two levels above this skill's SKILL.md file (the harness gave you that file's absolute path when the skill loaded); substitute it literally
[ -x "$FLOWCTL" ] || FLOWCTL=".flow/bin/flowctl"
```

**Inline skill (no `context: fork`)** - `AskUserQuestion` must stay reachable for the few facts seed cannot observe. Subagents cannot call blocking question tools (Claude Code issues #12890, #34592). On portable hosts without `AskUserQuestion`, fall back to a plain-text numbered prompt with a final `Other - type your own answer` option. For read-only scouts use `Task` with `subagent_type: Explore` (or the host's generic read-only dispatch with Edit/Write disallowed when Explore is unavailable).

## Autonomy refusal

`/flow-next:features` is user-invoked (or a host loop the human started). `flow --auto`, land, and every other autonomous driver must not dispatch it. Scan the autonomy-marker **namespace**, never a fixed two-var list. Any hit refuses with the typed one-line report and stops.

```bash
REFUSE=0
# Namespace scan over autonomy marker families. Never a fixed two-var list.
# Families: any FLOW_*AUTONOM* name, plus the mode:autonomous argument token.
if env | grep -E '^FLOW_[^=]*AUTONOM' >/dev/null 2>&1; then
  REFUSE=1
fi
case " ${ARGUMENTS:-} " in
  *" mode:autonomous "*) REFUSE=1 ;;
esac
if [ "$REFUSE" = "1" ]; then
  echo 'FEATURES_VERDICT=REFUSED features=0 reason="autonomy marker present; /flow-next:features is user-invoked only"'
  exit 2
fi
```

## Mode Detection

State-resolved, cwd-relative to the repo root (`.flow/features/` under the current working directory). No `.flow/features/` directory, or explicit init intent (`--init`, `init`, `mode:seed`, `--seed` in `$ARGUMENTS`), routes to **seed**. A present map with no init intent routes to **maintain**. Consumers elsewhere gate on directory existence only: no config key, no registration.

```bash
MODE="maintain"
if [ ! -d ".flow/features" ]; then
  MODE="seed"
fi
RAW_ARGS="${ARGUMENTS:-}"
for ARG in $RAW_ARGS; do
  case "$ARG" in
    --init|init|mode:seed|--seed) MODE="seed" ;;
  esac
done
printf 'MODE=%s\n' "$MODE"
```

| Mode | When | Behavior |
|------|------|----------|
| **seed** | `.flow/features/` absent, or explicit init intent | Interview the repo, prove each route with one live drive, write the index plus one file per proven feature. Explicit re-init over an existing map first requires `.flow/features/` to be CLEAN in git (`git status --porcelain -- .flow/features/` empty - uncommitted map edits could be overwritten or deleted unrecoverably; dirty ends `BLOCKED` asking to commit or stash). Then every pre-existing feature file is either re-proven this run (and re-indexed) or removed with the removal named in the verdict reason - a file neither re-proven nor removed cannot remain, and `SEEDED` over unproven leftovers has broken this. See [seed.md](seed.md). |
| **maintain** | `.flow/features/` present and no init intent | Audit-shaped pass over the existing map. See [maintain.md](maintain.md). |

## Interaction Principles

- **Interview the repo, not the user.** Surface, run command, drive mechanism, observable evidence, isolation: read them from the checkout. Ask only what cannot be observed.
- Ask via `AskUserQuestion` (call `ToolSearch` with `select:AskUserQuestion` first if its schema is not loaded). Fall back to numbered options in plain text only if the tool is unreachable or errors. Never silently skip the question.
- Prefer **multiple choice** when natural options exist. Lead with the recommended option and a one-sentence rationale.
- Do **not** ask before evidence is gathered. Observation first, questions second.
- Multi-surface repos (web + CLI) seed **per-surface feature groups** under one index. Enumeration is observation: each feature file carries `**Surface:**`; consumers select by surface + sub-feature IDs.

## Forbidden

- **Dispatch by an autonomous driver.** `flow --auto`, land, or any autonomy-marker hit: refuse. Cadence belongs to the human or their host loop.
- **Editing product code in maintain.** Maintain's edit scope is `.flow/features/` plus harness scripts the map owns. Product bugs are reported and kept out of the PR.
- **Merging.** Never `gh pr merge`, never `/flow-next:land`. A `changed` maintain PR stays open for the human or land.
- **Driving an instance this run did not start.** Doctor names the owner. An orphaned port from a crashed prior run ends `BLOCKED`; reclaim is left to the human. Never kill by process name - kill what this run started.
- **Setting `context: fork`** - blocking-question tools must stay reachable.
- **Duplicating the drive-skill ladder.** Live driving consumes [flow-next-drive](../flow-next-drive/SKILL.md) by pointer. A copy of CDP / agent-browser / Computer-Use actuation detail in this skill has broken this.
- **Writing an undriven feature file.** Nothing enters the map that was not driven once.
- **Treating the map as the intent source.** Specs and acceptance criteria stay the contract of what to prove. The map is how-to-drive only.

## Workflow

1. Run the autonomy-refusal fence. On refuse, the `FEATURES_VERDICT=REFUSED` line is the last line of the run.
2. Run the mode-detection fence. Honor `MODE`.
3. **seed** - execute [seed.md](seed.md) in order.
4. **maintain** - execute [maintain.md](maintain.md) in order.

## Terminal line

Every run ends with exactly one terminal line, the last line of the response, with nothing after it:

```text
FEATURES_VERDICT=<SEEDED|CLEAN|CHANGED|BLOCKED|REFUSED> features=<n> reason="<one line>"
```

| Verdict | When |
|---------|------|
| `SEEDED` | Seed landed at least one proven feature (partial seed names failures in `reason`) |
| `CLEAN` | Maintain: no map/harness change, no branch, no PR |
| `CHANGED` | Maintain: one PR of proven map/harness corrections only, or the pushed or local branch when no create command reaches the host or the user asked for less |
| `BLOCKED` | Named blocker (missing ship-name value, orphaned port, concurrent isolation failure, source-reader collapse of the pass, a failed ship step). Next run re-enters fresh; a failed ship step keeps the proven edits and names them. |
| `REFUSED` | Autonomy marker, no drivable surface, no usable driver on this host, or broken checkout |

Use `features=0` when nothing landed. `reason` is one line, quoted.

© Gordon Mickel · MIT · gmickel/flow-next

Similar skills

All skills for Testing and QA →

From the same set70

The whole set →
flow-next-spec-completion-review flow-next-spec-completion-review is a skill that checks whether a spec's tasks together meet its requirements. Run it before marking work on the spec complete. CX Codex +1 ★ 730repo stars flow-next-capture flow-next-capture synthesizes the active conversation context into a structured flow-next spec under .flow/specs/ using the bundled flowctl tool. CX Codex +1 ★ 730repo stars flow-next-prime flow-next-prime assesses whether a codebase is ready for agents and production, checks that commands run, then leads with a verdict and ranked next steps. CX Codex +1 ★ 730repo stars repo-scout repo-scout scans a repository for existing patterns, conventions and related code before an agent starts implementing a requested change. CX Codex ★ 730repo stars flow-next-sync flow-next-sync runs plan-sync by hand to bring downstream task specs back in line once the code has moved ahead, touching tasks still in todo or blocked. CX Codex +1 ★ 730repo stars flow-next-visual flow-next-visual is a Claude Code skill that turns specs, tasks, Git diffs, or discussion topics into compact Markdown digests. It activates when a visual outline is easier to scan. CX Codex +1 ★ 730repo stars flow-next-memory-migrate flow-next-memory-migrate converts legacy markdown memory records into structured YAML entries using the bundled flowctl CLI. CX Codex +1 ★ 730repo stars flow-next-flow flow-next-flow — a Flow-Next skill that routes work across stages: capture, refine, plan, work, QA, make-pr, and land. Runs on demand or with --auto for unattended end-to-end flows. CX Codex +1 ★ 730repo stars

Project sponsors

Companies that keep this analytics open