gmickel/flow-next/plugins/flow-next/skills/flow-next-map/SKILL.md
flow-next-map
Wrap `clawpatch map` to produce a semantic feature index of the repo (~20 languages, persisted at `.clawpatch/features/*.json`). Detects install, runs `clawpatch init` when `.clawpatch/` absent, invokes provider-free `clawpatch map --source heuristic` by default; `--source auto|agent` flows through as passthrough. Opt-in enrichment — scouts and prime read the resulting index, but flowctl never depends on clawpatch.
- Source repository stars
- 689
- Declared platforms
- 0
- Static risk flags
- 1
- Last source update
- 2026-08-28
- Source checked
- 2026-08-28
Decision brief
What it does: where it fits
Read workflow.md for full phase-by-phase execution.
Not for
- Tasks that require unconfirmed production actions or broad system permissions.
- Environments where the pinned source and install steps cannot be inspected.
Compatibility matrix
Platform support, with evidence labels
| Platform | Status | Evidence | What to check |
|---|---|---|---|
| Codex | Not declared | No explicit evidence | Portability before use |
| Claude Code | Not declared | No explicit evidence | Portability before use |
| Cursor | Not declared | No explicit evidence | Portability before use |
| Gemini CLI | Not declared | No explicit evidence | Portability before use |
Installation
Inspect first. Install second.
The source command is displayed only when detected. A safe inspection prompt is always available so your agent can explain every action before execution.
npx skills add https://github.com/gmickel/flow-next --skill "plugins/flow-next/skills/flow-next-map"Inspect the Agent Skill "flow-next-map" from https://github.com/gmickel/flow-next/blob/efe60be268df748bdfbfc546a38751f8cf26c912/plugins/flow-next/skills/flow-next-map/SKILL.md at commit efe60be268df748bdfbfc546a38751f8cf26c912. List every install step, command, network request, credential, file read/write, external action, and rollback step. Explain whether it fits my task. Do not install or execute anything until I approve.
Workflow
What the source asks the agent to do
- 01
Workflow
Execute the phases in workflow.md in order:
Pre-flight + config-state echo (R12) — one four-line block: clawpatch version + --source, CLAWPATCHPROVIDER env (or "none"), flow-next review backend (informational only), .clawpatch/ last-mapped timestamp (or "absent").Install detection (R1, R11) — command -v clawpatch + clawpatch --version. Missing → print pnpm add -g clawpatch install instructions verbatim and exit 1. When pnpm bin -g exits 0 but command -v clawpatch still empty, al…Version-range guard (R10) — parse clawpatch --version with (\d+\.\d+\.\d+); compare against SUPPORTEDCLAWPATCH. Outside range → one-line stderr warning naming expected vs found and continue (degrade — never block). - 02
Preamble
CRITICAL: flowctl is BUNDLED — NOT installed globally. which flowctl will fail (expected). Define once; subsequent blocks (here and in workflow.md) use $FLOWCTL:
CRITICAL: flowctl is BUNDLED — NOT installed globally. which flowctl will fail (expected). Define once; subsequent blocks (here and in workflow.md) use $FLOWCTL:Inline skill (no context: fork) — the map skill is fully non-interactive: install detection, version-range guard, clawpatch init, .clawpatch/.gitignore skeleton, and clawpatch map invocation all proceed without promptin… - 03
Input
Format: [--source ] [-- ]
Default (no args) → clawpatch map --source heuristic (provider-free, deterministic). Heuristic targets conventional app/framework layouts; unconventional repos (CLI tools, plugins, markdown/docs-heavy, non-standard mono…--source auto|agent → passthrough to clawpatch; user must have CLAWPATCHPROVIDER configured for these paths (clawpatch's own concern, not ours).-- → terminator; tokens after flow to clawpatch map (e.g. --since-ref origin/main, --paths src/). - 04
Version pin
Single source of truth for the supported clawpatch range. Workflow Phase 1 parses clawpatch --version with a tolerant (\d+\.\d+\.\d+) regex and compares against this range. Outside-range → warn one line to stderr and degrade (continue). Never block. Re-verify on each clawpatch m…
Single source of truth for the supported clawpatch range. Workflow Phase 1 parses clawpatch --version with a tolerant (\d+\.\d+\.\d+) regex and compares against this range. Outside-range → warn one line to stderr and de…clawpatch is pre-1.0 (v0.4.0, 2026-05-22; weekly minor releases). The README forecasts breaking changes between minor releases — tolerant parsing matters. - 05
Ralph-block (R13) — runs first, before everything else
/flow-next:map requires a user at the terminal for the install-prompt and init-prompt branches. Autonomous loops cannot install global npm packages or accept interactive consent. Decline-to-run when Ralph signals are set.
/flow-next:map requires a user at the terminal for the install-prompt and init-prompt branches. Autonomous loops cannot install global npm packages or accept interactive consent. Decline-to-run when Ralph signals are se…Decline-to-run only — nothing is written to $REVIEWRECEIPTPATH. That file belongs to the upstream review caller; a run that leaves any byte there under Ralph has corrupted an unrelated receipt and broken this. The skill…No env-var opt-in. Ralph never installs global tools or accepts interactive consent.
Permission review
Static risk signals and limitations
Runs scripts
The documentation asks the agent to run terminal commands or scripts.
**Install detection (R1, R11)** — `command -v clawpatch` + `clawpatch --version`. Missing → print `pnpm add -g clawpatch` install instructions verbatim and exit 1. When `pnpm bin -g` exits 0 but `command -v clawpatch` still empty, also prinEvidence record
Why each signal appears
| Signal | Value | Evidence type | Meaning |
|---|---|---|---|
| Quality score | 95/100 | Computed | Documentation, specificity, maintenance, and trust rules |
| Repository stars | 689 | Source | Repository attention, not individual Skill quality |
| Compatibility | 0 platforms | Source | Declared in the catalog source record |
| Usage guide | automated source guide | Editorial | Generated or reviewed according to the visible evidence level |
Pinned source
Provenance and original SKILL.md
- Repository
- gmickel/flow-next
- Skill path
- plugins/flow-next/skills/flow-next-map/SKILL.md
- Commit
- efe60be268df748bdfbfc546a38751f8cf26c912
- License
- MIT
- Collected
- 2026-08-28
- Default branch
- main
View the original SKILL.md
/flow-next:map — wrap clawpatch map for a semantic feature index
Read workflow.md for full phase-by-phase execution.
Wrap the upstream clawpatch CLI's map subcommand. Default invocation is provider-free (--source heuristic) — zero LLM calls, zero API spend, deterministic mapper. Output lands at .clawpatch/features/*.json (Zod-validated upstream, schemaVersion: 1). Scout enrichment and the /flow-next:prime DE7 nudge read the resulting index; this skill is the install/init/invoke surface.
Role: thin shell-out wrapper. flowctl never imports or requires clawpatch; the skill is the only flow-next surface that touches it.
Preamble
CRITICAL: flowctl is BUNDLED — NOT installed globally. which flowctl will fail (expected). Define once; subsequent blocks (here and in workflow.md) use $FLOWCTL:
FLOWCTL="${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) — the map skill is fully non-interactive: install detection, version-range guard, clawpatch init, .clawpatch/.gitignore skeleton, and clawpatch map invocation all proceed without prompting the user. No blocking-question tool is required or used.
Input
Arguments: $ARGUMENTS
Format: [--source <heuristic|auto|agent>] [-- <extra clawpatch args>]
- Default (no args) →
clawpatch map --source heuristic(provider-free, deterministic). Heuristic targets conventional app/framework layouts; unconventional repos (CLI tools, plugins, markdown/docs-heavy, non-standard monorepos) may map to 0 features — Phase 5 surfaces a--source=auto|agentsuggestion when that happens. --source auto|agent→ passthrough to clawpatch; user must haveCLAWPATCH_PROVIDERconfigured for these paths (clawpatch's own concern, not ours).--→ terminator; tokens after flow toclawpatch map(e.g.--since-ref origin/main,--paths src/).
Passthrough boundary. The slash-command host delivers $ARGUMENTS as a single string; the skill word-splits on whitespace. Passthrough is therefore token-level (whitespace-separated), not full shell-verbatim — tokens containing literal spaces or shell metacharacters that require shell quoting will not survive. Globs (*, ?) are protected from expansion (set -f before the parse) so they reach clawpatch untouched. Users needing complex quoting should run clawpatch map directly.
flow-next's review backend config (rp / codex / copilot / none) stays out of clawpatch. clawpatch's provider matrix (codex / acpx / claude / cursor / grok / opencode / pi) is orthogonal — a run that sets CLAWPATCH_PROVIDER from the flow-next backend has broken this. The Phase 0 echo reports the backend as informational only.
Version pin
SUPPORTED_CLAWPATCH=">=0.4.0 <0.5.0"
Single source of truth for the supported clawpatch range. Workflow Phase 1 parses clawpatch --version with a tolerant (\d+\.\d+\.\d+) regex and compares against this range. Outside-range → warn one line to stderr and degrade (continue). Never block. Re-verify on each clawpatch minor release.
clawpatch is pre-1.0 (v0.4.0, 2026-05-22; weekly minor releases). The README forecasts breaking changes between minor releases — tolerant parsing matters.
Ralph-block (R13) — runs first, before everything else
/flow-next:map requires a user at the terminal for the install-prompt and init-prompt branches. Autonomous loops cannot install global npm packages or accept interactive consent. Decline-to-run when Ralph signals are set.
if [[ -n "${REVIEW_RECEIPT_PATH:-}" || "${FLOW_RALPH:-}" == "1" ]]; then
if [[ -n "${REVIEW_RECEIPT_PATH:-}" ]]; then
TRIGGER="REVIEW_RECEIPT_PATH"
else
TRIGGER="FLOW_RALPH"
fi
echo "Error: /flow-next:map declines under Ralph ($TRIGGER set); rerun interactively." >&2
exit 2
fi
Decline-to-run only — nothing is written to $REVIEW_RECEIPT_PATH. That file belongs to the upstream review caller; a run that leaves any byte there under Ralph has corrupted an unrelated receipt and broken this. The skill exits at line 1 of the workflow under Ralph; install/init paths are unreachable.
No env-var opt-in. Ralph never installs global tools or accepts interactive consent.
Workflow
Execute the phases in workflow.md in order:
- Pre-flight + config-state echo (R12) — one four-line block: clawpatch version +
--source,CLAWPATCH_PROVIDERenv (or"none"), flow-next review backend (informational only),.clawpatch/last-mapped timestamp (or"absent"). - Install detection (R1, R11) —
command -v clawpatch+clawpatch --version. Missing → printpnpm add -g clawpatchinstall instructions verbatim and exit 1. Whenpnpm bin -gexits 0 butcommand -v clawpatchstill empty, also print the PNPM_HOMEbin/hint (runpnpm setup, re-source shell rc). No auto-install. - Version-range guard (R10) — parse
clawpatch --versionwith(\d+\.\d+\.\d+); compare againstSUPPORTED_CLAWPATCH. Outside range → one-line stderr warning naming expected vs found and continue (degrade — never block). - Init (R2) — when
.clawpatch/absent, runclawpatch initfirst. After clawpatch creates.clawpatch/project.json+.clawpatch/config.json, write a self-contained.clawpatch/.gitignoreskeleton (skill owns this write — STRATEGY zero-dep means flowctl never references clawpatch). - Map invocation (R1) —
clawpatch map --source <SOURCE> [extra passthrough]. Default<SOURCE>isheuristic(always passed explicitly — never rely on clawpatch's default in case upstream changes it). clawpatch streams stdout live; the skill does not buffer. - Result summary — print path to
.clawpatch/features/, count of feature files, last-mapped timestamp; suggestflowctl repo-map listand the/flow-next:plan//flow-next:capturepaths that consume it.
Sharing contract — local-only by design
The .clawpatch/.gitignore skeleton this skill writes is * + !.gitignore — everything under .clawpatch/ is git-ignored; only the .gitignore itself is tracked. The feature index is local-per-developer, not committed.
This is a deliberate design choice for a pre-1.0 mapper:
- No PR review noise from regenerated feature data on every
clawpatch maprun. - No merge conflicts on
features/*.jsonwhen two branches mapped at different SHAs. - No coupling of PR review to mapper-output drift as clawpatch schema bumps land (weekly minor releases at the time of writing).
- Onboarding cost is low —
--source heuristicis a fast filesystem walk; new contributors regenerate locally in seconds.
Teams that want a shared, in-repo feature index can edit .clawpatch/.gitignore directly (e.g. !features/, !project.json, ignore only .cache/ and *.log). The skill is idempotent and won't clobber a customized .gitignore on re-run. This is unsupported — be prepared for review noise and merge conflicts; document the choice in your team's CLAUDE.md / AGENTS.md. See flow-next.dev/skills/map for the full trade-off table.
Forbidden
- Auto-installing clawpatch. The skill detects and instructs; users install with their own permission. Global npm installs are user-consent territory.
- Proxying flow-next's review backend into
CLAWPATCH_PROVIDER. Orthogonal matrices. clawpatch users configure clawpatch directly. - Auto-upgrading
--sourcetoautooragentwhen heuristic coverage looks weak. Users opt up explicitly via--source. - Touching the repo
.gitignore. The.clawpatch/.gitignoreskeleton is self-contained inside.clawpatch/so a full deletion of that directory removes both data and ignore rules in one step. - Writing to
$REVIEW_RECEIPT_PATHfrom the Ralph-block path — see R13 above. The receipt belongs to the upstream review caller; the Ralph branch is decline-to-run, not a receipt producer. - Importing or requiring clawpatch from flowctl. flowctl never references this skill or clawpatch — uninstall promise (
rm -rf .flow/) stays intact and zero-dep STRATEGY track is preserved. - Network calls beyond what clawpatch itself does. The wrap is local-only; clawpatch's network behavior is upstream's concern.
- Running under Ralph — hard-blocked by R13 above.
Frequently asked questions
What to verify before installation and use
What does the flow-next-map source document cover?
Read workflow.md for full phase-by-phase execution.
How do I install flow-next-map?
The source record exposes this install command: npx skills add https://github.com/gmickel/flow-next --skill "plugins/flow-next/skills/flow-next-map". Inspect the command and pinned source before running it.
Which permission-related actions were detected?
Static rules flagged exec-script in the source; the page lists the matching lines and excerpts.
Alternatives
Compare before choosing
gmickel/flow-next
flow-next-map
Build a semantic feature index of the repo via clawpatch map (opt-in). Use when asked to map the repo.
garrytan/gbrain
bulk-ingestion
End-to-end discipline for turning any large data source (audio libraries, email takeouts, document corpora, chat exports, API dumps) into brain pages at scale. The lifecycle spine: SCHEMA → ACCESS → TRIAL → EVALUATE → IMPROVE → CODIFY → TEST → SKILLIFY → BULK → MONITOR. State is tracked in a durable JSON manifest (see MANIFEST-PATTERN.md) so any crash, session boundary, or subagent fan-out resumes from ground truth instead of memory.
alirezarezvani/claude-skills
app-store-optimization
App Store Optimization (ASO) toolkit for researching keywords, analyzing competitor rankings, generating metadata suggestions, and improving app visibility on Apple App Store and Google Play Store. Use when the user asks about ASO, app store rankings, app metadata, app titles and descriptions, app store listings, app visibility, or mobile app marketing on iOS or Android. Supports keyword research and scoring, competitor keyword analysis, metadata optimization, A/B test planning, launch checklist
wanshuiyin/Auto-claude-code-research-in-sleep
citation-audit
Use it for operations and research tasks; the detail page covers purpose, installation, and practical steps.