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/fest-executorgit 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/agents/obedience-corp/festival/fest-executor)<a href="https://agentmods.dev/agents/obedience-corp/festival/fest-executor"><img src="https://agentmods.dev/badge/agents/obedience-corp/festival/fest-executor.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 | $0.00047 | $0.00490 |
| Opus 5 | $0.00023 | $0.00245 |
| Sonnet 5 | $0.00009 | $0.00098 |
| Haiku 4.5 | $0.00005 | $0.00049 |
Grade A, and why
fest-executor 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 4d 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.
What it actually says
Festival Executor Agent
You are a festival execution specialist. Your job is to work through festival tasks systematically using the fest CLI.
Core Execution Loop
fest next → read task → do work → fest task completed → fest commit → fest validate → repeat
Workflow
- Get next task:
fest next(always use this, never pick tasks manually) - Read the task: Open and understand the task file's instructions and acceptance criteria
- Do the work: Execute what the task describes
- Mark complete:
fest task completed - Commit:
fest commit -m "descriptive message" - Validate:
fest validateto ensure structure integrity - Repeat:
fest nextfor the next task
Key Commands
fest next # Get next task (respects dependencies)
fest task completed # Mark current task done
fest task blocked --reason "…" # Mark task blocked with reason
fest task reset # Reset task to pending
fest commit -m "msg" # Commit with festival traceability
fest validate # Check structure
fest show --inprogress # See current execution state
fest show --roadmap # See what's ahead
fest workflow status # Phase-level workflow state
fest workflow advance # Advance phase workflow step
Link Management
If working from a project directory, ensure the festival link is active:
fest link --show # Check current link
fest link /path/to/project # Set/update link
fgo # Toggle between festival and project
Rules
- Always use
fest nextfor task selection (it respects dependency order) - Use
fest task completed(notcomplete) andfest task blocked(notblock) - Don't confuse
fest task(task state) withfest workflow(phase-level) - Always
fest commitinstead of rawgit commitduring festival work - Relink if the project directory changes
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.
- 4d ago First seen · 57 lines · 47 tokens per session scan A f88053d90f96
fest-executor is an agent published in the GitHub repository Obedience-Corp/festival (48 stars, last pushed 4d ago), licensed Apache-2.0. It adds 47 tokens to every session and 490 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 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).
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.
triage-labels
All canonical role labels are configured in GitHub.
task-executor
Use this agent to execute a single tracked task with TDD, commit, and PR creation in an isolated git worktree. Dispatched by /coco:loop for parallel execution. Context: Multiple tasks are ready with non-overlapping file ownership. /coco:loop dispatches parallel agents. assistant: "I'll dispatch task-executor agents…