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.
git 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/plugins/obedience-corp/festival/gemini-extension)<a href="https://agentmods.dev/plugins/obedience-corp/festival/gemini-extension"><img src="https://agentmods.dev/badge/plugins/obedience-corp/festival/gemini-extension/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/plugins/obedience-corp/festival/gemini-extension"><img src="https://agentmods.dev/badge/plugins/obedience-corp/festival/gemini-extension.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
festival 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.
What it actually says
{
"_generated": "GENERATED by packaging/generate.mjs from claude-plugin/. Do not edit; edit the source and re-run 'just plugin generate'.",
"name": "festival",
"version": "1.4.1",
"description": "Festival Methodology: goal-oriented project management for human-AI development workflows. Provides fest and camp CLI integration, automatic installation, and methodology guidance.",
"contextFileName": "GEMINI.md"
}
What ships with it
55 files beside gemini-extension.json in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- examples/claude-code-workflow/after/CLAUDE.md 692 B
- examples/claude-code-workflow/after/festivals/active/api-rate-limit/001_IMPLEMENT/01_build-rate-limit/01_discover-middleware.md 561 B
- examples/claude-code-workflow/after/festivals/active/api-rate-limit/001_IMPLEMENT/01_build-rate-limit/02_add-rate-limit-middleware.md 541 B
- examples/claude-code-workflow/after/festivals/active/api-rate-limit/001_IMPLEMENT/01_build-rate-limit/03_document-rate-limits.md 469 B
- examples/claude-code-workflow/after/festivals/active/api-rate-limit/CONTEXT.md 480 B
- examples/claude-code-workflow/after/festivals/active/api-rate-limit/FESTIVAL_GOAL.md 457 B
- examples/claude-code-workflow/before/SESSION_NOTES.md 756 B
- examples/claude-code-workflow/README.md 1.3 KB
- scripts/check_release_channel_tags.sh 3.4 KB runs code
- scripts/check-doc-sync.sh 3.8 KB runs code
- scripts/ci/windows-archive-container-failure-inner.ps1 450 B runs code
- scripts/ci/windows-archive-container-inner.ps1 1.7 KB runs code
- scripts/ci/windows-archive-container-journey-inner.ps1 25 KB runs code
- scripts/ci/windows-archive-container-proof.ps1 12 KB runs code
- scripts/ci/windows-installer-cli-container-inner.ps1 20 KB runs code
- scripts/ci/windows-public-marketplace-container-inner.ps1 6.8 KB runs code
- scripts/ci/windows-public-scoop-container-inner.ps1 6.4 KB runs code
- scripts/ci/windows-public-scoop-container-proof.ps1 3.5 KB runs code
- scripts/ci/windows-scoop-container-inner.ps1 7.4 KB runs code
- scripts/ci/windows-scoop-container-proof.ps1 2.8 KB runs code
- scripts/ci/windows-terminal-proof/go.mod 1.1 KB
- scripts/ci/windows-terminal-proof/go.sum 3.7 KB
- scripts/ci/windows-terminal-proof/main_windows.go 9.7 KB
- scripts/ci/windows-terminal-proof/screen_test.go 831 B
- scripts/ci/windows-terminal-proof/screen.go 638 B
- scripts/completion-assets.sh 9.0 KB runs code
- scripts/completion-clis.txt 284 B
- scripts/completions.sh 1.2 KB runs code
- scripts/discord_content_feed.py 14 KB runs code
- scripts/lib/submodules.sh 1.4 KB runs code
- scripts/normalize_cli_docs.py 3.7 KB runs code
- scripts/publish_existing_release_npm.sh 1.5 KB runs code
- scripts/publish_marketplace_entry.sh 3.8 KB runs code
- scripts/publish_npm_package.sh 2.5 KB runs code
- scripts/smoke_beginner_path.sh 13 KB runs code
- scripts/submit-go-dependency-snapshot.sh 5.3 KB runs code
- scripts/test_claude_plugin.sh 56 KB runs code
- scripts/test_cli_docs_profile.sh 943 B runs code
- scripts/test_completion_assets.sh 6.7 KB runs code
- scripts/test_discord_content_feed.py 11 KB runs code
- scripts/test_docs_discovery.mjs 11 KB runs code
- scripts/test_docs_onboarding.mjs 6.1 KB runs code
- scripts/test_install_shell.sh 7.6 KB runs code
- scripts/test_marketplace_publish.sh 12 KB runs code
- scripts/test_npm_windows_channel.js 746 B runs code
- scripts/test_starter_setup.sh 2.0 KB runs code
- scripts/test_verify_published_windows_scoop.py 4.4 KB runs code
- scripts/tool-versions.sh 2.2 KB runs code
- scripts/upsert_marketplace_index.py 793 B runs code
- scripts/verify_published_windows_scoop.py 4.4 KB runs code
- scripts/verify_scoop_manifest.py 3.2 KB runs code
- scripts/verify_windows_archive.py 2.9 KB runs code
- templates/agentic-feature-build/AGENT_PROMPT.md 1.2 KB
- templates/agentic-feature-build/FEATURE_PLAN.md 1.8 KB
- templates/agentic-feature-build/README.md 700 B
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 1ae09f69f080
- 1mo ago First seen · 8 lines scan A 1c65ee530374
festival is a plugin published in the GitHub repository Obedience-Corp/festival (67 stars, last pushed today), licensed Apache-2.0. Its token cost is not measured: this kind of file is read by the harness, not the model. 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 2026-09-08.
Other plugins, from other repositories
prd-workflow
RFC-driven development workflow: vague idea → verified PRD → features → rules → sequenced RFCs → reviewed, tested code.
standup-autopilot
Turns what your agents ACTUALLY did into a standup: captured from session transcripts (not commits/tickets, which miss uncommitted work, real test exit codes, and unresolved errors) and rolled up cross-repo. Stop/SessionEnd snapshot each session's outcome (task, branch + diffstat, tests + exit codes, PRs, blockers) to.
bounty-board
Turns your repo's tech debt into an aging bounty economy. A SessionStart hook scans tracked files and prices each TODO/FIXME/HACK/skip as a wanted-poster bounty whose XP grows with its git-blame age, injects the top 3 as opportunistic side quests, and, via a PostToolUse hook, verifies and pays out bounties that…
people-management
AI-augmented management tooling for people managers. Surfaces the right context at the right time: before meetings, during 1:1 prep, when triaging messages, or reviewing customer status. Adapts to your org's performance and management frameworks. Augments managers, never automates.
instruction-placement
Routes agent instructions to the surface that loads them at the right time. audit finds conventions narrower than the always-loaded CLAUDE.md or AGENTS.md holding them, or stranded in docs Claude never loads, and proposes a destination with a validated paths glob; safety-class content is never demoted. realign applies.
ops
Structured non-code project management for Claude Code: planning, execution, knowledge persistence, and autonomous work loops for research, strategy, and content projects. 9 skills, 5 agents, 7 commands.