workflow-reference

workflow-reference is a skill for Claude Code from neuromechanist/research-skills. It costs 75 tokens per session (2,086 once invoked), scanned A, original, BSD-3-Clause.

A reference for developing a large feature in separate stages, using Git branches, worktrees, and GitHub issues. A worktree is a separate working copy of the same repository, and each stage is delivered as a reviewable pull request.

In plain words
What is it for?
Use it to plan feature phases, create epic branches and sub-issues, work in separate Git worktrees, define completion checks, and prepare staged pull requests.
Why use it?
It helps break large work into testable parts and keeps each part isolated for development and review. It also provides rules for deciding whether work should be one stage or several.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: names the TodoWrite tool; mentions Codex.

Needs its repository: it reads a path above its own folder, which exists only inside the repository. The line is worktree_base: "../epic-dashboard".

Part of the project plugin — 15 skills, 5 commands, 3 agents shipped together

Good fit Use it to plan feature phases, create epic branches and sub-issues, work in separate Git worktrees, define completion checks, and prepare staged pull requests.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/neuromechanist/research-skills
agentmods
npx agentmods add skills/neuromechanist/research-skills/workflow-reference

Made for: Claude Code.

Or install project, the plugin that ships this one along with the rest of its 15 skills, 5 commands, 3 agents.

Wrote 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.

agentmods badge for workflow-reference

README.md
[![agentmods](https://agentmods.dev/badge/skills/neuromechanist/research-skills/workflow-reference/github.svg)](https://agentmods.dev/skills/neuromechanist/research-skills/workflow-reference)
Your own site
<a href="https://agentmods.dev/skills/neuromechanist/research-skills/workflow-reference"><img src="https://agentmods.dev/badge/skills/neuromechanist/research-skills/workflow-reference/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for workflow-reference

Your own site · 80×15
<a href="https://agentmods.dev/skills/neuromechanist/research-skills/workflow-reference"><img src="https://agentmods.dev/badge/skills/neuromechanist/research-skills/workflow-reference.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 75 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,086 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Excessive Agency · line 175
    Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
    Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
How audits are shown
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 5.1 $0.00075 $0.02086
Opus 5 $0.00037 $0.01043
Sonnet 5 $0.00015 $0.00417
Haiku 4.5 $0.00007 $0.00209

Measured 10d ago against content hash 87c460450608, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

workflow-reference 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 10d 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.

plugins/project/skills/workflow-reference/SKILL.md · 227 lines

How it starts

The opening of the file, as written. The whole thing — 227 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Epic/Sprint Development Workflow Reference

Procedural reference for multi-phase feature development using git worktrees, GitHub issues with sub-issues, and phased PR delivery.

Phase Sizing and Epic-vs-Single Decision

One phase = one independently reviewable and testable PR: roughly one subsystem, one migration, or up to ~500 net lines of non-generated change.

  • The description contains 2+ such units -> epic (this workflow).
  • Exactly one unit -> single-phase shortcut (below), or simply the engineering-loop skill without epic machinery.
  • Unsure how to break a description into phases: each phase must have its own testable Definition of Done; if two candidate phases can only be tested together, they are one phase.

Slug derivation for names: take the phase title, drop stopwords, keep 2-3 words with the object noun first, kebab-case ("backend-metrics", "sync-engine"; never "implement-the-new-backend-metrics").

Related skills: implementation-planning (writing each phase plan), agent-fanout (parallel implementers, one worktree each), engineering-loop (the inner loop within a phase), debugging (when a phase's tests fail for unclear reasons).

Model handoff by phase

The lead model owns epic decomposition, architecture, observation, approval-gate decisions, verification, and synthesis. In Codex use Sol; in Claude use Fable when available, otherwise Opus. Once architecture is approved, an intermediate planner may produce the detailed phase brief (Codex Terra; Claude Sonnet only when no design judgment remains). A named worker implements that brief in the isolated worktree (Codex Luna or Claude Sonnet). Fresh worker reviewers validate each phase, while high-risk or architectural findings return to the lead. Close/remove one-off agents after their reports are incorporated.

Branch Strategy Decision Tree

Determine the integration branch and branching model:

  1. Integration branch detection:
    • If develop branch exists (local or remote): integration branch = develop
    • Otherwise: integration branch = default branch (main or master)

Read the full file on GitHub · 227 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. 10d ago First seen · 227 lines · 75 tokens per session scan A 87c460450608

Subscribe to this mod's changes

workflow-reference is a skill published in the GitHub repository neuromechanist/research-skills (45 stars, last pushed 7d ago), licensed BSD-3-Clause. It adds 75 tokens to every session and 2,086 once invoked, about $0.0004 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.

Related

Other skills, from other repositories

close-task-commit-push-pr

Close the active backlog task (detected from branch name), commit all changes, push to remote, and open a pull request. Use when the user says "close task and ship it", "close task commit push pr", or invokes /close-task-commit-push-pr.

devoxx/DevoxxGenieIDEAPlugin · 64 tokens

start-task

Create a feature branch for a backlog task, switch to it, and start implementation. Use when the user says "start task-123", "work on task-123", "implement task-123", or invokes /start-task with a task ID.

devoxx/DevoxxGenieIDEAPlugin · 54 tokens

github-notification-triage

Triage GitHub notifications and issue/PR queues.

notque/vexjoy-agent · 18 tokens

utility-pm-release-conductor

Walk the guided 6-gate release runbook (G0 readiness, G1 adversarial review, G2 version bump and CHANGELOG, G2.5 commit and re-verify, G3 tag and push, G4 post-tag hygiene) via the pm-release-conductor sub-agent. Refuses gate bypasses and tags only the re-verified SHA. Use when cutting a pm-skills release.

product-on-purpose/pm-skills · 90 tokens

github-triage

Triage GitHub issues through a label-based state machine with interactive grilling sessions. Use when user wants to triage issues, review incoming bugs or feature requests, prepare issues for an AFK agent, or manage issue workflow.

sammcj/agentic-coding · 50 tokens

releasing-godot-prompter

Use when cutting a GodotPrompter release or bumping its version — the version-bump sequence, tag-triggered workflow, and the marketplace manifests that must follow.

jame581/GodotPrompter · 44 tokens