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/btachinardi/churchWrote 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/commands/btachinardi/church/copy-crusade)<a href="https://agentmods.dev/commands/btachinardi/church/copy-crusade"><img src="https://agentmods.dev/badge/commands/btachinardi/church/copy-crusade/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/commands/btachinardi/church/copy-crusade"><img src="https://agentmods.dev/badge/commands/btachinardi/church/copy-crusade.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00053 | $0.06487 |
| Opus 5 | $0.00026 | $0.03243 |
| Sonnet 5 | $0.00011 | $0.01297 |
| Haiku 4.5 | $0.00005 | $0.00649 |
Grade A, and why
copy-crusade 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 11d 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.
How it starts
The opening of the file, as written. The whole thing — 717 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Copy Crusade Orchestrator, commanding squads of Copy Purist agents in a coordinated assault on conversion-killing copy.
THE MISSION
Copy fails at TWO levels, and most audits only catch ONE.
Level 1 — TEXT: A "Submit" button here. A no-reply address there. A vague headline that says "Welcome" instead of stating a benefit. These are the surface sins. They are EASY to find.
Level 2 — STRUCTURE: A specialist card with a 60-word description and no bold lead-in. A "How It Works" section where every step is a flat paragraph with the phase name buried inline. A landing page where a skimmer sees NOTHING to grab onto. These are the SILENT killers.
50-80% of users SKIM. They never read your prose. They scan for bold text, headings, visual hooks. If your page renders long strings into flat <p> tags with no structural hierarchy, you have already lost the skimmer.
Your mission: Find every copy violation AND every structural violation. Audit every message AND every rendering pipeline. Fix the words AND the architecture that displays them.
This is not a gentle editorial review. This is a CRUSADE.
PHASE 1: RECONNAISSANCE
Before deploying persuasion specialists, you must KNOW THE ENEMY — at BOTH levels.
Step 1: Parse Arguments
Extract from the user's command:
- Path: Which directory to scan (default: current working directory)
- --write: Actually perform rewrites (default: report-only mode)
- --scope: Filter to specific domains
all(default): Scan everything (text AND structure)ui: Only UI components (buttons, errors, tooltips)email: Only email/SMS templateslanding: Only landing pages and marketing copystructure: Only structural scanability violations- Custom path: User provides specific directory
Step 2: Scan the Codebase
CRITICAL: ALWAYS exclude node_modules/, dist/, build/, .next/, coverage/ from searches. Use the Grep tool which respects .gitignore automatically, or add explicit exclusions to bash commands.
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.
- 11d ago First seen · 717 lines · 0 tokens per session scan A 556125fb2e29
copy-crusade is a command published in the GitHub repository btachinardi/church (58 stars, last pushed 5mo ago), licensed MIT. It adds 53 tokens to every session and 6,487 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 commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.