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 agents/obedience-corp/festival/claude-codegit clone --depth 1 https://github.com/Obedience-Corp/festivalWhat 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 | $0.00000 | $0.01977 |
| Opus 5 | $0.00000 | $0.00988 |
| Sonnet 5 | $0.00000 | $0.00395 |
| Haiku 4.5 | $0.00000 | $0.00198 |
Grade C, and why
claude-code scanned grade C with 2 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 2d 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
curl -fsSL https://raw.githubusercontent.com/Obedience-Corp/festival/main/install.sh | bash Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -fsSL https://raw.githubusercontent.com/Obedience-Corp/festival/main/install.sh | bash How it starts
The opening of the file, as written. The whole thing — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claude Code
Claude Code runs Festival through a plugin. The plugin does not replace the loop: the loop is still fest next, do the task, fest task completed, fest commit. What the plugin adds is that the methodology skills are already loaded, the fest and camp verbs have slash-command shortcuts, and two agents are available for planning and execution.
Order matters. Install the binaries first, then open a campaign, then install the plugin.
1. Install Festival
Pick one:
# Homebrew
brew install --cask Obedience-Corp/tap/festival
# npm, pnpm, or bun
npm install -g @obedience-corp/festival
# Shell script
curl -fsSL https://raw.githubusercontent.com/Obedience-Corp/festival/main/install.sh | bash
Then check all three binaries answer:
fest --version
camp --version
festival --version
If either one is missing or resolves somewhere you did not expect, festival doctor reports the installer's view of your PATH, sources, and receipts. Full install options are on the installation page.
The plugin's session-start hook installs both binaries for you (section 5), so this step is belt and braces. Do it anyway: your shell has fest and camp before the first session starts, and you can confirm where they resolve from rather than finding out mid-loop.
2. Open a campaign
A campaign is the directory Festival works in. Create one and stay at its root:
mkdir my-campaign && cd my-campaign
camp init
camp init writes the campaign layout, initializes git, and creates the festivals tree. It also writes two context files, or rather one file and one link:
$ ls -l AGENTS.md CLAUDE.md
-rw-r--r-- AGENTS.md
lrwxr-xr-x CLAUDE.md -> AGENTS.md
That symlink is the point. Claude Code reads CLAUDE.md, Festival writes AGENTS.md, and the link means one file serves both. Edit AGENTS.md; your Claude Code sessions see the same content.
camp init also links the campaign skills into .claude/skills and .agents/skills. Those are camp's own skills for working in a campaign, and they are separate from the plugin bundle described below.
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.
- 2d ago First seen · 164 lines · 0 tokens per session scan C 43f74239bcd1
claude-code is an agent published in the GitHub repository Obedience-Corp/festival (48 stars, last pushed 3d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,977 tokens. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
tools
Tools give agents the ability to interact with the outside world — reading files, making HTTP requests, connecting to MCP servers, calling APIs, or running custom Python functions. They are configured in the tools list of a role definition. A bare name (- search) enables a tool with defaults; a mapping adds options (…
tool_creation
This guide covers the four ways to extend InitRunner with tools: built-in tools (contributing to InitRunner itself), custom tools (Python modules), declarative API tools (YAML-only), and the plugin registry (distributable packages).
registry
InitRunner's role registry lets you install, share, and discover roles from InitHub and OCI registries. Roles are downloaded, validated, and saved to /.initrunner/roles/ where they integrate automatically with the CLI.
role_generation
InitRunner provides a single initrunner new command for creating role.yaml files. It supports multiple seed modes (templates, AI generation, examples, hub bundles, or local files) and an interactive refinement loop for iterating on the YAML before saving. Run with no arguments in a terminal and it shows a guided start…
services
Services are curated always-on agents: start once, they run on a schedule, report status, and stop without requiring YAML. Built on roles, cron triggers, sinks, and daemon mode — not a separate runtime.
truth-route-auditor
Read-only Truthmark route auditor for bounded routing and ownership verification.