fest-standalone-workflows

fest-standalone-workflows is a skill for Cursor from Obedience-Corp/festival. It costs 62 tokens per session (1,021 once invoked), scanned A, original, Apache-2.0.

A lightweight guided workflow for work that can live in any ordinary folder. It stores a short sequence of steps in WORKFLOW.md and moves through them one at a time.

In plain words
What is it for?
Use it for code reviews, release runbooks, investigations, or other small jobs that need a plan, actions, and checkpoints.
Why use it?
It provides a repeatable checklist without requiring the larger structure used for long, multi-stage projects.

Skill for Cursor

Written for Cursor: a Cursor plugin manifest.

Part of the festival plugin — 12 skills, 11 commands shipped together

Good fit Use it for code reviews, release runbooks, investigations, or other small jobs that need a plan, actions, and checkpoints.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/obedience-corp/festival/fest-standalone-workflows
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.

Any agent
npx skills add Obedience-Corp/festival --skill fest-standalone-workflows
Clone the repo
git clone --depth 1 https://github.com/Obedience-Corp/festival

Made for: Cursor.

Or install festival, the plugin that ships this one along with the rest of its 12 skills, 11 commands.

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 fest-standalone-workflows

README.md
[![agentmods](https://agentmods.dev/badge/skills/obedience-corp/festival/fest-standalone-workflows/github.svg)](https://agentmods.dev/skills/obedience-corp/festival/fest-standalone-workflows)
Your own site
<a href="https://agentmods.dev/skills/obedience-corp/festival/fest-standalone-workflows"><img src="https://agentmods.dev/badge/skills/obedience-corp/festival/fest-standalone-workflows/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 fest-standalone-workflows

Your own site · 80×15
<a href="https://agentmods.dev/skills/obedience-corp/festival/fest-standalone-workflows"><img src="https://agentmods.dev/badge/skills/obedience-corp/festival/fest-standalone-workflows.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 62 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,021 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 pass 7 Sept 2026
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 $0.00062 $0.01021
Opus 5 $0.00031 $0.00511
Sonnet 5 $0.00012 $0.00204
Haiku 4.5 $0.00006 $0.00102

Measured 10d ago against content hash b7c7387e9198, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

fest-standalone-workflows 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.

.cursor-plugin/skills/fest-standalone-workflows/SKILL.md · 136 lines

How it starts

The opening of the file, as written. The whole thing — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Fest Standalone Workflows

Use a standalone WORKFLOW.md when work needs a guided step loop in an ordinary directory, without setting up a full festival (phases/sequences/tasks).

Thin-start loop:

WORKFLOW.md -> fest next -> do step -> fest workflow advance -> repeat

When to Use This vs. a Full Festival

  • Standalone workflow: a short, repeatable checklist that can live in any directory: a code-review checklist, a release-cut runbook, a one-off investigation. Minimal ceremony, no phases/sequences.
  • Full festival: multi-phase work that needs planning, sequencing, and quality gates over an extended effort. Use fest create festival instead (see the fest-planning skill).

Create

Run from the directory that should own the workflow:

mkdir -p my-workflow && cd my-workflow

fest create workflow my-workflow --steps '{
  "title": "My Workflow",
  "description": "A lightweight guided loop.",
  "steps": [
    {
      "name": "PLAN",
      "goal": "Decide what needs to happen.",
      "actions": ["Write the goal.", "List the unknowns."],
      "checkpoint": "none"
    },
    {
      "name": "DO",
      "goal": "Do the work.",
      "actions": ["Make the change.", "Validate it."],
      "checkpoint": "verification"
    }
  ]
}'

fest next

This scaffolds WORKFLOW.md, initializes .workflow/ runtime state, and starts a tracked run, so fest next works immediately.

fest workflow create <name> is an alias of fest create workflow <name> and accepts the same flags. Use whichever noun you reach for first.

For human interactive creation, run the command without --steps from a TTY:

fest create workflow my-workflow

It prompts for title, intent, and step lines in Name|Goal form.

Flags

  • --steps '<json>' / --steps-file <file>: agent mode, inline JSON or a JSON file. See the step schema below.
  • --agent: strict agent mode (implies --json).
  • --type <type>: standalone workflow type (default task).
  • --no-init: advanced mode. Writes WORKFLOW.md only, without initializing .workflow/ runtime state or starting a run. fest next still works in this mode, but reports the workflow as not-started; the first mutating command (fest workflow advance) bootstraps a tracked run lazily. Use this when you want to author the document before committing to a tracked run.
  • --path <dir> / --festival <root>: target a festival phase instead of standalone mode. Inside a festival phase, or with either of these flags set, the command writes the phase's WORKFLOW.md with no standalone runtime, so do not pass these when you want a standalone workflow.

Read the full file on GitHub · 136 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 · 136 lines · 62 tokens per session scan A b7c7387e9198

Subscribe to this mod's changes

fest-standalone-workflows is a skill published in the GitHub repository Obedience-Corp/festival (49 stars, last pushed today), licensed Apache-2.0. It adds 62 tokens to every session and 1,021 once invoked, about $0.0003 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.