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-executiongit 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-execution)<a href="https://agentmods.dev/skills/obedience-corp/festival/fest-execution"><img src="https://agentmods.dev/badge/skills/obedience-corp/festival/fest-execution.svg" alt="Measured on agentmods" 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 | $0.00038 | $0.00674 |
| Opus 5 | $0.00019 | $0.00337 |
| Sonnet 5 | $0.00008 | $0.00135 |
| Haiku 4.5 | $0.00004 | $0.00067 |
Grade A, and why
fest-execution scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 7d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Festival Execution
Core Loop
fest next → do work → fest task completed|blocked → fest commit → fest validate → repeat
Link + Navigation
Festival commands from a project directory depend on an active festival-project link.
# In festival directory: link the execution project path
fest link /absolute/path/to/project
fest link --show
# Shell navigation (after `eval "$(fest shell-init zsh)"`)
fgo # toggle festival ↔ linked project
fgo project # jump to linked project
fgo fest # jump back to linked festival
If the execution project path changes (moved repo, new worktree), relink before continuing work.
Task State
fest task completed
fest task blocked --reason "..."
fest task reset
Do not mix command families:
fest taskmutates task status.fest workflowadvances phase-level workflow/gate steps.
Visibility and Dependencies
fest show --inprogress --watch
fest show --roadmap
fest deps
Workflow Steps (Phase-Level)
fest workflow status
fest workflow advance
fest workflow skip --reason "..."
Lifecycle Hooks
Task state changes can fire configured hooks. Inspect the effective set before assuming a transition is inert:
fest hooks list
Verbs: task_start, task_complete, sequence_complete, phase_complete,
gate_approve.
task_startfires on the first transition into work, whichever surface causes it:fest status set in_progress --task <id>, a direct completion, or the firstfest task update <percent>above zero. Resuming or re-marking in progress never re-fires it;fest task resetclears the recorded start.task_completefires on every completion surface, not justfest task completed.
Task document frontmatter binds names only. Bare pre/post bind around the
terminal verb; the nested start: stage binds around task_start and is
honored on task documents only.
hooks:
pre: [lint]
post: [approval_judge]
start:
pre: [anchor]
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 First seen · 107 lines · 38 tokens per session scan A c8021e884cd2
fest-execution is a skill published in the GitHub repository Obedience-Corp/festival (50 stars, last pushed 4d ago), licensed Apache-2.0. It adds 38 tokens to every session and 674 once invoked, about $0.0002 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
artifact-metadata
Manage artifact metadata, versioning, ownership, and review history across the SDLC lifecycle.
steward-prep-delivery
Steward-assisted prep for filing issues and PRs — environment capture, template selection, duplicate detection, delivery-policy compliance check.
contribute-start
Initialize an AIWG contribution workflow by creating a feature branch, configuring DCO, and linking a tracking issue.
aiwg-delivery-pr
AIWG-specific delivery pull request workflow; explicit alias for aiwg-pr, not a generic repository PR guide.
github-navigator
GitHub operations via gh CLI. CRITICAL: Use instead of WebFetch for any github.com URL or GitHub repo path like owner/repo. Use when the user asks to inspect repositories, files, issues, pull requests, releases, Actions runs, or repository structure. Use when the user says 'show README', 'list issues', 'check PR'…
continue
Autonomous work — find and execute ready tasks.