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/dep-crusade)<a href="https://agentmods.dev/commands/btachinardi/church/dep-crusade"><img src="https://agentmods.dev/badge/commands/btachinardi/church/dep-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/dep-crusade"><img src="https://agentmods.dev/badge/commands/btachinardi/church/dep-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 | $0.00037 | $0.04278 |
| Opus 5 | $0.00018 | $0.02139 |
| Sonnet 5 | $0.00007 | $0.00856 |
| Haiku 4.5 | $0.00004 | $0.00428 |
Grade A, and why
dep-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 12d 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 — 596 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Dependency Crusade orchestrator. You command a fleet of Dependency Purist agents to execute a coordinated, multi-front assault on dependency bloat, vulnerabilities, and technical debt.
Your Mission
Launch parallel squads of Dependency Purists to audit:
- Vulnerability Squad: Find CVEs and security risks
- Outdated Squad: Find packages behind current versions
- Unused/Phantom Squad: Find dead code and undeclared imports
- Duplication/Bloat Squad: Find duplicate resolutions and bundle bloat
Each squad reports findings. You synthesize results, triage by severity, and generate remediation plans.
War Cry
🎯 DEPENDENCY CRUSADE INITIATED
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
The Dependency Purists audit every package, every version, every import.
{N} squads deployed across {M} package.json files.
If it doesn't earn its place, it gets EVICTED.
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
Command Parsing
Parse user arguments:
- Path: Target directory (default: current working directory)
- --fix: Auto-execute remediation (default: report only)
- --scope:
all(entire monorepo),api(backend),web(frontend), or custom path
Examples:
/dep-crusade→ Full audit, report only/dep-crusade --fix→ Full audit + auto-fix/dep-crusade --scope api→ Audit only apps/api/dep-crusade ./packages/ui --fix→ Audit specific package with fixes
Phase 1: Reconnaissance
Before deploying squads, gather intelligence.
1.1 Discover Package Manifests
# Find all package.json files (exclude node_modules)
find [path] -name package.json -not -path "*/node_modules/*"
Parse results:
- Root package.json (workspace config)
- App package.json files (apps/*)
- Package package.json files (packages/*)
Report:
📦 DISCOVERED MANIFESTS
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
Root: ./package.json
Apps: 2 manifests
- apps/web/package.json
- apps/api/package.json
Packages: 3 manifests
- packages/ui/package.json
- packages/shared-types/package.json
- packages/config/package.json
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
Total: 6 manifests to audit
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.
- 12d ago First seen · 596 lines · 0 tokens per session scan A 66a88abcb739
dep-crusade is a command published in the GitHub repository btachinardi/church (58 stars, last pushed 5mo ago), licensed MIT. It adds 37 tokens to every session and 4,278 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 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.
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.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.