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.
npx skills add Obedience-Corp/festival --skill fest-standalone-workflowsgit clone --depth 1 https://github.com/Obedience-Corp/festivalWrote 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.
[](https://agentmods.dev/skills/obedience-corp/festival/fest-standalone-workflows)<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.
<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>- NVIDIA SkillSpector pass
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.
| Model | Per session | Once 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 |
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.
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 festivalinstead (see thefest-planningskill).
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 (defaulttask).--no-init: advanced mode. WritesWORKFLOW.mdonly, without initializing.workflow/runtime state or starting a run.fest nextstill 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'sWORKFLOW.mdwith no standalone runtime, so do not pass these when you want a standalone workflow.
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.
- 10d ago First seen · 136 lines · 62 tokens per session scan A b7c7387e9198
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.
Other skills, from other repositories
config-validator
Validate AIWG configuration files and project setup for correctness and completeness.
link-check
Verify @file references in AIWG skills and agents against the linking contract — per-file or corpus-wide, with optional auto-fix.
activity-log
Query and manage the unified .aiwg/activity.log chronological record of AIWG-managed workflow operations.
checkpoint
Create, list, or recover mid-workflow checkpoints so interrupted work resumes from a known-good position.
mention-conventions
Display @-mention naming conventions and placement rules.
validate-metadata
Validate AIWG extension definitions against the metadata schema and report errors with field names, line numbers, and remediation hints.