Claude Skill MartBrowse skillsQuick linesLearn by videoTerminal guideWhat is a Skill?
 
← Back to list

Anti-Ceremony (Process Overhead Guard)

A single artifact-free CONTINUE/STOP judgment run before planning, so agent work stays tied to the caller-visible outcome instead of ceremony.

AutomationAdvanced★ 433⑂ 40AI score 6/10Last updated: Sep 4, 2026

What it does

  • Freezes the caller-visible outcome in one short statement.
  • Parks proposed process work that has no concrete consumer, gated subject, observed defect, or retirement condition (dashboards, second audit passes, control docs).
  • Names the implementation or independent proof still missing and the stop condition that ends the traversal.
  • Returns only a 6-field YAML block (decision, reason, frozen_outcome, parked_process_work, remaining_proof, stop_condition) — no files written, no tracker mutations.
  • Runs a fuller keep/park/drop honesty audit only when the caller explicitly writes full anti-ceremony audit.

Who it's for

  • Teams running RPI-style (Research–Plan–Implement) agent workflows that keep drowning in planning artifacts.
  • Tech leads and PMs who want to cut "reporting about reporting" each cycle.
  • Claude Code users whose agents produce plan documents instead of shipped changes.

Examples

  1. Pre-Plan gate: "Outcome: the gate check lists the probe-coverage row / Proposed: a coverage dashboard plus a second audit pass" → both are parked, remaining proof is "gate row green in CI", decision CONTINUE.
  2. Already proved: if the frozen outcome is already verified in CI, the skill returns STOP with a one-sentence reason, blocking extra paperwork.
  3. Full audit: ask for a "full anti-ceremony audit" to review retro templates, weekly reports, and checklists, returning keep/park/drop for each.

· · · Install guide · · ·

Try it now, no install

Paste this into Claude to use the skill without installing anything.

Read the instructions in this file and follow them to help me:
https://raw.githubusercontent.com/boshu2/agentops/HEAD/images/gemini/skills/anti-ceremony/SKILL.md

What I want: (describe your task here)

If Claude can't open the link, open it yourself and paste the contents instead.

↓ If it works for you, download the ZIP below and install it. Then it runs on its own — no pasting each time.

Install in the Claude app (no terminal)
  1. Download the ZIP with the button below.
  2. In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
  3. Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.
↓ Download ZIP
Install in Claude Code

Let Claude do it — paste this into Claude Code

Install the skill I found on Claude Skill Mart.
Copy the images/gemini/skills/anti-ceremony folder from the GitHub repo boshu2/agentops into my ~/.claude/skills/anti-ceremony/.
When it's done, tell me in one line what this skill can do.

Install with a command instead

git clone https://github.com/boshu2/agentops.git && mkdir -p ~/.claude/skills && cp -r agentops/images/gemini/skills/anti-ceremony ~/.claude/skills/

⚠ This is a third-party skill. Check the source repository before installing.

  1. Open a terminal.
  2. Clone the repository: git clone https://github.com/boshu2/agentops.git
  3. Create the skills folder: mkdir -p ~/.claude/skills
  4. Copy the skill: cp -r agentops/images/gemini/skills/anti-ceremony ~/.claude/skills/
  5. It reads references/boundaries.md from the sibling rpi skill, so copy that too: cp -r agentops/images/gemini/skills/rpi ~/.claude/skills/
  6. Restart Claude Code and confirm anti-ceremony appears in your skill list.
  7. Usage: right before planning, supply the outcome, the proposed process work, remaining proof, and a stop condition, then ask for the anti-ceremony decision.
View source on GitHub ↗License: Apache-2.0