Flow Next WorkSAFE
Faster than your agent alone. And better. A workflow plugin that takes a bug, idea or ticket to a verified pull request: specs, cross-model review by risk, live QA, receipts in your repo. Claude Code · Codex · Cursor · Droid · Grok Build · OpenCode · Muse Code.
Overview
Faster than your agent alone. And better. A workflow plugin that takes a bug, idea or ticket to a verified pull request: specs, cross-model review by risk, live QA, receipts in your repo. Claude Code · Codex · Cursor · Droid · Grok Build · OpenCode · Muse Code.
bd2f79679176OBSERVED · 2026-10-14Host compatibility
What the documentation claims. We have not run a compatibility test.
| Host | Status | Notes |
|---|---|---|
| claude-code | mentioned | |
| codex | mentioned | |
| copilot | mentioned | |
| cursor | mentioned |
What it tells the agent
The instruction file, verbatim from the audited commit — this is the text the model reads, and the surface the audit's instruction layer examines. Quoted here so you can judge it without cloning anything.
---
name: flow-next-work
description: Execute a Flow spec or task systematically with git setup, task tracking, quality checks, and commit workflow. Run only by /flow-next:work or when flow-next-flow routes a spec here; any other request to implement, build or work on a spec, Flow-Next named or not, goes to flow-next-flow. Triggers on /flow-next:work with Flow IDs (fn-1-add-oauth, fn-1-add-oauth.2, or legacy fn-1, fn-1.2, fn-1-xxx, fn-1-xxx.2).
user-invocable: false
---
# Flow work
Execute a plan systematically. Focus on finishing.
**`.flow/` is the only task tracker.** A run that recorded task state in a markdown TODO, a plan file, TodoWrite, or any other tracker has broken this — all task state is read and written via `flowctl`.
## Preamble
**CRITICAL: flowctl is BUNDLED — NOT installed globally.** `which flowctl` will fail (expected). Define once; subsequent blocks (here and in `phases.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"
```
**Hard requirements (non-negotiable):**
- **Every completed task passes through `flowctl done` and a verified `done` status.** A task treated as finished while `flowctl show <task>` still reads `todo` or `in_progress` has broken this.
- **Staging is the files you changed plus `.flow/` (`git add -- <files> .flow/`), never `git add -A`** — `.flow/` carries the run's task state; files a test run or tool wrote stay out of the diff. A commit whose diff omits the run's `.flow/` writes has broken this.
- **Completion is claimed only after `flowctl show <task>` reports `status: done`.** A completion claim printed ahead of that read has broken this.
- **`flow-next:flow-next-impl-review` is dispatched only on a green tree.** A review sent while tests or Quick commands are red has broken this.
**Role**: execution lead, plan fidelity first.
**Goal**: complete every task in order with tests.
## Autonomous Mode (questions off, no receipt obligations)
Before gates, treat this host-expanded block as literal prompt data, never shell:
<work-arguments>
$ARGUMENTS
</work-arguments>
Strip standalone whitespace token `mode:autonomous` into `WORK_ARGS`; preserve
all else verbatim (spaces/quotes/globs). Set/export `AUTONOMOUS=1` if found or
`FLOW_AUTONOMOUS=1`; otherwise set/export `AUTONOMOUS=0`.
Continue with `WORK_ARGS`; carry the exported marker into later shell fragments.
If `AUTONOMOUS=1`: read [references/autonomous-defaults.md](references/autonomous-defaults.md)
before any question, and:
- **Branch defaults deterministically to `--branch=new`** when no explicit branch option is present — under autonomy "the user's answer" never exists, and defaulting to the current branch could commit straight to main. A chained spec (`flowctl spec chain` names a parent) forks from the parent's remote tip instead of main (phases.md Phase 2). **Name the new branch exactly the spec's `branch_name` field** (`$FLOWCTL show <spec-id> --json | jq -r '.branch_name'`) — the branch matrix of `flow --auto`, its all-done PR probe, and make-pr's branch-match spec detection all key on that name; an ad-hoc name breaks continuity across hops and invocations.
## Input
Full request after mode parsing: `$WORK_ARGS`
Accepts:
- Flow spec ID `fn-N-slug` (e.g., `fn-1-add-oauth`) or legacy `fn-N`/`fn-N-xxx` to work through all tasks
- Flow task ID `fn-N-slug.M` (e.g., `fn-1-add-oauth.2`) or legacy `fn-N.M`/`fn-N-xxx.M` to work on single task
- Markdown spec file path (creates spec from file, then executes)
- Idea text (creates minimal spec + single task, then executes)
- Chained instructions like "then review with /flow-next:impl-review"
If no input provided, ask for it.
## FIRST: Parse Options
### Option Parsing (skip questions if found in arguments)
Parse `WORK_ARGS` for these patterns. If found, use them and skip corresponding questions:
**Branch mode**:
- `--branch=current` or `--current` or "current branch" or "stay on this branch" → current branch
- `--branch=new` or `--new-branch` or "new branch" or "create branch" → new branch
- `--branch=worktree` or `--worktree` or "isolated worktree" or "worktree" → isolated worktree
**Review mode**:
- `--review=<codex|copilot|cursor|claude|host|none>`, or the same backend named in words
("review with codex", "host review", "skip review"); `--no-review` = `none`
- `--review=rp` or `--review=export` → removed: say "RepoPrompt review (rp, export) was removed in flow-next 8.0.0; review backends: claude, codex, copilot, cursor, host." once, never pass it as `REVIEW_MODE`, and continue as when no review backend is configured
(All non-`none` review modes route through `flow-next:flow-next-impl-review`, which resolves the
configured/overridden backend — codex, copilot, cursor, claude, or host — itself.)
**No-plan (direct spec execution)**:
- `--no-plan` or "no plan" or "skip planning" or "work directly without planning" → set `NO_PLAN=1`; it pre-answers Phase 1's zero-task fork so the fork's ask never fires when intent is stated
- Implementation review, coverage, completion policy and opt-in QA remain unchanged on this route.
- The fork's semantics (ask, autonomous refusal, durable choice, implicit-task mint) live in phases.md Phase 1's gated [references/no-plan-route.md](references/no-plan-route.md), read only when the fork fires
**Autonomous mode**:
- `AUTONOMOUS=1` → use the defaults above.
### If the options are absent from the arguments
**If `AUTONOMOUS=1` (autonomous mode):** ask nothing — apply the autonomous defaults and continue to the workflow.
**Otherwise (interactive)**: do not ask about the branch. Stay on the current branch when it is
not the default branch, otherwise create a new one (named for tTrust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | NA |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- none-observed
- Shell
- none-observed
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (0)
No findings outside the package's declared scope.
Gates applied: no_behavioural_pass.
bd2f79679176full audit observations/trust-audit/skill/gmickel__flow-next-work.json · Report an issue / request a re-scanAudit history
Every audit this skill has had.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-14 | bd2f79679176 | SAFE | B | 89 | first audit |
Questions
What does the Flow Next Work skill do?
Faster than your agent alone. And better. A workflow plugin that takes a bug, idea or ticket to a verified pull request: specs, cross-model review by risk, live QA, receipts in your repo. Claude Code · Codex · Cursor · Droid · Grok Build · OpenCode · Muse Code.
Is Flow Next Work safe to install?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean skill reads B.
What can Flow Next Work access on my machine?
The audit observed no filesystem, network or shell use at all in its source.
Which assistants does Flow Next Work work with?
Its documentation mentions claude-code, codex, copilot and cursor. That is what the text claims, not a compatibility test we ran.
How current is this page?
The grade is for one exact copy of the source (bd2f79679176), read on 2026-10-14. The repository is watched, and a new audit runs when it changes — this is the first audit.