feature-workflow

A command that turns a high-level development plan into a sequence of planned, checked, implemented, and reviewed work items. Each work item includes acceptance criteria, tests, and rollback notes.

In plain words
What is it for?
Use it for multi-step feature work that needs planning, impact analysis, specialized coding agents, tests, and explicit acceptance before completion.
Why use it?
It reduces the risk of starting implementation before understanding project rules, affected files, dependencies, and expected behavior. The workflow pauses when the plan conflicts with the project's specifications.

Command for Claude Code

Install

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.

agentmods
npx agentmods add commands/xiaolai/vmark/feature-workflow
Clone the repo
git clone --depth 1 https://github.com/xiaolai/vmark

Made for: Claude Code.

Per session 11 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 596 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00011 $0.00596
Opus 5 $0.00005 $0.00298
Sonnet 5 $0.00002 $0.00119
Haiku 4.5 $0.00001 $0.00060

Measured yesterday against content hash f71621e59642, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

feature-workflow 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 yesterday.

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.

.claude/commands/feature-workflow.md · 62 lines

How it starts

The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Feature Workflow (Gated Orchestrator)

Goal: take a high-level plan and drive it to completion using specialized subagents, TDD gates, and explicit acceptance.

Inputs

  • work-name: short slug (e.g. file-mgmt-rebuild-phase0)
  • Optional: an existing plan doc to refine.

Workflow (always in this order)

  1. Plan (Planner agent)

    • Create or refine a modular plan in the project docs directory.
    • Break into Work Items with explicit acceptance criteria, tests, and rollback notes.
  2. Spec Check (Spec Guardian agent)

    • Validate plan vs specs and project rules in AGENTS.md and .claude/rules/*.md.
    • Stop if specs conflict or constraints are violated.
  3. Impact (Impact Analyst agent)

    • For each Work Item, map the minimal file set, dependency edges, and risks.
    • Propose the smallest correct change boundaries.
  4. Implement (Implementer agent)

    • For each Work Item, do a preflight investigation before writing tests:
      • Reproduce/describe current behavior and expected behavior.
      • Trace the exact call chain and identify the smallest test seam.
      • Confirm the minimal file impact; update the Impact map if needed.
      • Subagent delegation is encouraged for this "map and report" step.
    • For each Work Item: write the test first (RED), implement (GREEN), refactor safely.
    • Encourage subagent delegation for large/mechanical diffs; always review + run gates after.
    • Keep side effects isolated; keep changes local; keep files under ~300 lines.
  5. Test (Test Runner agent)

    • Run pnpm check:all (and cargo test when Rust changes).
    • If UI flows are impacted, request the user to run the app and use Tauri MCP for E2E.
  6. Audit (Auditor agent)

    • Review diffs for correctness, architecture drift, and rule violations.
    • If issues found: loop back to Implement for fixes.
  7. Manual Test Guide (Manual Test Author agent)

    • Update manual testing docs incrementally per Work Item.
    • Ensure final “end-to-end” guide exists and is coherent.

Read the full file on GitHub · 62 lines

Changes

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.

  1. yesterday First seen · 62 lines · 11 tokens per session scan A f71621e59642

Subscribe to this mod's changes

feature-workflow is a command published in the GitHub repository xiaolai/vmark (544 stars, last pushed 2d ago), licensed ISC. It adds 11 tokens to every session and 596 once invoked, about $0.0001 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.