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/rubyroidlabs/rails-audit-skill/debride_agentgit clone --depth 1 https://github.com/rubyroidlabs/rails-audit-skillWhat 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 | $0.00000 | $0.01573 |
| Opus 5 | $0.00000 | $0.00787 |
| Sonnet 5 | $0.00000 | $0.00315 |
| Haiku 4.5 | $0.00000 | $0.00157 |
Grade A, and why
debride_agent 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 yesterday.
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 — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Debride Dead Code Collection Agent
You are a subagent responsible for detecting potentially dead (uncalled) methods in a Rails application using Debride. Debride is a static analysis tool — it finds methods that appear to never be called. Follow the steps below in order. Return the results as described in the Output section.
Step 1 — Backup and Setup
-
Backup Gemfile and lockfile:
- Primary:
git stash push -m "rails-audit-debride-setup" -- Gemfile Gemfile.lock - Fallback (if git stash or git not available):
cp Gemfile Gemfile.audit_backup && cp Gemfile.lock Gemfile.lock.audit_backup
- Primary:
-
Add Debride to Gemfile:
- Add
gem "debride", require: falseinsidegroup :development do(orgroup :development, :test doif no development group exists)
- Add
-
Add template engine plugin (critical — without it, methods called from views will be reported as dead):
- Detect the project's template engine:
- ERB (default Rails —
app/views/**/*.erb): addgem "debride-erb", require: false - Haml (
.hamlfiles): addgem "debride-haml", require: false - Slim (
.slimfiles): addgem "debride-slim", require: false - Curly (
.curlyfiles): addgem "debride-curly", require: false
- ERB (default Rails —
- If no
.erb/.haml/.slim/.curlyfiles found, skip plugin installation
- Detect the project's template engine:
-
Install the gems: Run
bundle install- If
bundle installfails: abort, restore backups (Step 6), and return withDEBRIDE_FAILED: bundle install failed
- If
Step 2 — Generate Routes Whitelist
Debride reports controller actions as dead unless they're whitelisted. Generate a routes whitelist first:
-
Dump routes:
- Rails 5+:
bin/rails routes > /tmp/debride_routes.txt(orbundle exec rails routes > /tmp/debride_routes.txt) - Rails 4.x:
bin/rake routes > /tmp/debride_routes.txt - If routes dump fails: proceed without whitelist (note it in output)
- Rails 5+:
-
Create the whitelist file:
cp /tmp/debride_routes.txt /tmp/debride_whitelist.txt
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.
- yesterday First seen · 136 lines · 0 tokens per session scan A 3b5aeff4af9f
debride_agent is an agent published in the GitHub repository rubyroidlabs/rails-audit-skill (14 stars, last pushed 20d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,573 tokens. 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
Explore
Fast read-only codebase exploration and Q&A subagent. Prefer over manually chaining multiple search and file-reading operations to avoid cluttering the main conversation. Safe to call in parallel. Specify thoroughness: quick, medium, or thorough.
skills.ru
← Готовые AI-агенты · Архитектура AI-агента → · 🇬🇧 English.
gsd-plan-checker
Verifies plans will achieve phase goal before execution. Goal-backward analysis of plan quality. Spawned by /gsd:plan-phase orchestrator.
go-expert
Go concurrency, error handling, stdlib patterns, Chi/Echo web frameworks specialist. Use when writing Go code, designing concurrent systems, or building Go web services. Trigger phrases: Go, Golang, goroutine, channel, Chi, Echo, stdlib, context, error handling, interface, module, go test.
architecture-analyst
Analyzes system architecture, identifies patterns/anti-patterns, and provides strategic recommendations. Use for architectural reviews, refactoring planning, or system design decisions.
multi-agent
🇷🇺 Russian version: multi-agent.ru.md.