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 festival-intakegit 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/festival-intake)<a href="https://agentmods.dev/skills/obedience-corp/festival/festival-intake"><img src="https://agentmods.dev/badge/skills/obedience-corp/festival/festival-intake/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/festival-intake"><img src="https://agentmods.dev/badge/skills/obedience-corp/festival/festival-intake.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 | $0.00119 | $0.00984 |
| Opus 5 | $0.00060 | $0.00492 |
| Sonnet 5 | $0.00024 | $0.00197 |
| Haiku 4.5 | $0.00012 | $0.00098 |
Grade A, and why
festival-intake 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 7d 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 — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Festival Intake
This is the front door. Every other camp skill assumes the user already knows what a festival is. This one does not, and it must fire before they do.
When it fires, you owe the user the six steps below, in order. Do not skip straight to creating things.
Step 1: Size it out loud
Say which gear this is and why, in one line, before doing anything else. The user learns the system has three gears by watching you pick one.
| Signal | Route |
|---|---|
| One file, one session, reversible | Answer in chat. Create nothing. |
| Linear, a handful of steps, one repo | fest create workflow <name> |
| Multi-phase, multi-repo, needs review gates, or outlives a session | fest create festival |
Most requests are the first row. Reaching for a festival on small work is a failure mode, not thoroughness. When it is genuinely between two rows, pick the smaller one and say you can promote it later.
Step 2: Show the shape, then ask
Before scaffolding anything, present the proposed phases and the sequences under each, and get a yes.
You already have everything you need to do this at that point in the conversation, so it costs nothing. It is the user's one chance to redirect before work gets written to disk, and it is what makes the rest of the run trustworthy.
Step 3: Plan through the loop, not by scaffolding
Create the festival, then drive fest next and answer what it asks.
Do not scaffold every phase and sequence up front and fill in the
[REPLACE] markers afterward. That path looks faster and is the single worst
thing you can do to a festival:
- Scaffolding ten sequences at once writes hundreds of unfilled markers.
fest validatedrops to 0 the moment they exist, and stays there.- The pressure is then to fill markers with plausible filler to restore the score, which produces a green festival full of worthless tasks.
fest next walks you through planning one decision at a time and never opens
that window. The loop is the planning process, not just the execution process.
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.
- 7d ago Changed 8bd5ace10dff
- 11d ago First seen · 94 lines · 119 tokens per session scan A 9680ca7fa13a
festival-intake is a skill published in the GitHub repository Obedience-Corp/festival (49 stars, last pushed yesterday), licensed Apache-2.0. It adds 119 tokens to every session and 984 once invoked, about $0.0006 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.
hook-enable
Enable the AIWG context hook in platform context files without re-deploying.
mention-conventions
Display @-mention naming conventions and placement rules.