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 agentmods add skills/obedience-corp/festival/campaign-commitnpx skills add Obedience-Corp/festival --skill campaign-commitgit 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/campaign-commit)<a href="https://agentmods.dev/skills/obedience-corp/festival/campaign-commit"><img src="https://agentmods.dev/badge/skills/obedience-corp/festival/campaign-commit.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00053 | $0.00597 |
| Opus 5 | $0.00026 | $0.00298 |
| Sonnet 5 | $0.00011 | $0.00119 |
| Haiku 4.5 | $0.00005 | $0.00060 |
Grade A, and why
campaign-commit 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 today.
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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Camp Commit Decision
A camp was previously called a campaign; this skill applies whichever word the user uses.
Decision
- Project change (submodule, linked project, or worktree):
camp p commit -m "msg" - Festival task execution:
fest commit -m "msg" - Camp root files:
camp commit -m "msg"(stages all root-level changes; submodule refs excluded by default) - Camp root, scoped to specific paths:
git add <paths>thencamp commit --all=false -m "msg"(commits only what is staged) - Intentional root pointer sync:
camp refs-sync [submodule...]
Festival Commits Cover the Linked Project
When a festival or sequence has a linked project, fest commit makes up to two
commits even when you run it from inside the festival:
- a project commit staging the project's changes, skipped when the project is clean
- a camp root commit staging only festival-scoped files, the camp's
.campaign/fest/state, and the submodule pointer
So during festival execution do not run camp p commit first and fest commit
after. One fest commit covers both sides. Use --no-root to skip the camp
root commit.
A festival with no linked project makes the single camp root commit only.
Deferred Commit Queue
Camp defers its own bookkeeping commits so they do not hold the terminal. The queue is machine-local and disposable; git is the record.
camp jobs # what is queued, running, or failed
camp jobs --json # same, for agents
camp jobs retry all # requeue everything that failed
camp jobs drop <id> # give up on a failed job, keeping its content
camp jobs drop --running <id> # a stalled job, and the worker holding it
camp jobs drain # wait for every lane, then exit
Dropping a job never discards work: the content stays uncommitted in the working
tree for the next ordinary commit. If camp jobs reports a job as stalled, a
commit message writer stopped answering; --running is what ends that wait.
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.
- today Changed · +2 lines · +4 tokens per session 2cadc90088b6
- 4d ago First seen · 56 lines · 49 tokens per session scan A d7597ff82b1f
campaign-commit is a skill published in the GitHub repository Obedience-Corp/festival (49 stars, last pushed yesterday), licensed Apache-2.0. It adds 53 tokens to every session and 597 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
Vizra ADK Evaluation Framework
Test and evaluate AI agents with automated evaluations, assertions, and LLM-as-a-Judge patterns.
Vizra ADK Memory System
Implement persistent memory, session context, and vector memory (RAG) for AI agents.
Vizra ADK Tool Creation
Build custom tools for Vizra ADK agents - includes patterns for database, API, file, and email tools.
Vizra ADK Agent Creation
Create AI agents with Vizra ADK - includes patterns for customer service, data analysis, and content generation agents.
Vizra ADK Workflows
Orchestrate complex multi-agent workflows - sequential, parallel, conditional, and loop patterns.
email-triage
Classify incoming emails into triage categories using content analysis, sender profile memory, and thread detection. Produces a category (URGENT, REPLYNEEDED, FYI, NEWSLETTER, NOTIFICATION, SPAM) with confidence and reasoning.