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 skills/slbug/claude-ruby-grape-rails/investigatenpx skills add slbug/claude-ruby-grape-rails --skill investigategit clone --depth 1 https://github.com/slbug/claude-ruby-grape-railsWrote 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/skills/slbug/claude-ruby-grape-rails/investigate)<a href="https://agentmods.dev/skills/slbug/claude-ruby-grape-rails/investigate"><img src="https://agentmods.dev/badge/skills/slbug/claude-ruby-grape-rails/investigate.svg" alt="Measured on agentmods" 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 | $0.00047 | $0.00898 |
| Opus 5 | $0.00023 | $0.00449 |
| Sonnet 5 | $0.00009 | $0.00180 |
| Haiku 4.5 | $0.00005 | $0.00090 |
Grade A, and why
rb:investigate 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 5d 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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Investigate Ruby Bugs
Run a structured investigation instead of guessing.
STEP 0: Read the investigation discipline references
Read ${CLAUDE_SKILL_DIR}/references/discipline.md and
${CLAUDE_SKILL_DIR}/references/error-patterns.md. Apply the
verify-loop discipline + error-classification rubric as the
canonical procedure.
Investigation Tracks
- request path and route trace
- data and transaction analysis
- background job / Redis analysis
- verification and reproduction loop
Default Tools
bundle exec rspec path/to/spec.rb:LINEorbin/rails testbundle exec rails runnerpsqlfor SQL inspectionredis-clifor queue/cache inspection- app logs and Sidekiq logs
Output
Write a short investigation report with:
- observed behavior
- likely root cause
- confirming evidence
- safest next step (
/rb:planor/rb:quick)
Agent Dispatch
This is a skill (/rb:investigate), not an agent. Do NOT spawn
investigate or rb-investigate via the Agent tool. For agent-based deep
investigation, use deep-bug-investigator
(subagent_type: "ruby-grape-rails:deep-bug-investigator"). When spawning,
pass an explicit output path in the prompt
(.claude/investigations/deep-bug-investigator/{slug}-{datesuffix}.md);
the agent writes its findings to that file and returns a ≤300-word chat
summary. Read the file for the full report.
If the agent's return text matches the pause signature in
${CLAUDE_PLUGIN_ROOT}/references/agent-resume.md, follow that protocol
to resume the agent before treating the artifact as missing.
Gotchas
- Re-probing ruled-out hypotheses. Check
## Ruled Outscratchpad section FIRST. Don't re-run grep / Read on file already eliminated. - "Looks like X" without backtrace. Stack frame top-to-bottom is the only acceptable evidence for "the cause is in module X". Pattern matching against error message text is hypothesis, not evidence.
- Premature root-cause naming. State observed symptoms before hypothesizing cause. "Test fails on line 42 with NameError" is fact; "the bug is in Y constant" is hypothesis until reproduced.
- Skipping reproduction step. Always write a minimal failing spec before any code change. Cannot reproduce → no root cause.
What ships with it
5 files beside SKILL.md 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.
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.
- 5d ago First seen · 89 lines · 47 tokens per session scan A 981df9137241
rb:investigate is a skill published in the GitHub repository slbug/claude-ruby-grape-rails (7 stars, last pushed today), licensed MIT. It adds 47 tokens to every session and 898 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 2026-08-31.
Other skills, from other repositories
rspec
This skill should be used when the user asks to "write specs", "create spec", "add RSpec tests", "fix failing spec", or mentions RSpec, describe blocks, it blocks, expect syntax, test doubles, or matchers. Should also be used when editing spec.rb files, working in spec/ directory, planning implementation phases that…
activerecord
This skill should be used when the user asks to "write a migration", "add a column", "add column to table", "create an index", "add a foreign key", "set up associations", "fix N+1 queries", "optimize queries", "add validations", "create callbacks", "use eager loading", or mentions ActiveRecord, belongsto, hasmany…
draper-decorators
This skill should be used when the user asks to "create a decorator", "write a decorator", "move logic into decorator", "clean logic out of the view", "isn't it decorator logic", "test a decorator", or mentions Draper, keeping views clean, or representation logic in decorators. Should also be used when editing…
mcp-server
This skill should be used when the user asks to "create an MCP server", "build MCP tools", "define MCP prompts", "register MCP resources", "implement Model Context Protocol", or mentions the mcp gem, MCP::Server, MCP::Tool, JSON-RPC transport, stdio transport, or streamable HTTP transport. Should also be used when…
ratatui-ruby
This skill should be used when the user asks to "create a TUI", "terminal interface", "terminal UI", "ratatui", "ratatui-ruby", "inline viewport", "full-screen terminal app", "terminal widgets", "tui.draw", "tui.pollevent", or mentions RatatuiRuby.run, managed loop, terminal rendering, Tea MVU, or building CLI…
dragonruby
This skill should be used when the user asks to "create a game", "make a game", "game development", "dragonruby", "drgtk", "game loop", "tick method", "sprite rendering", "game state", or mentions args.outputs, args.state, args.inputs, coordinate system, collision detection, animation frames, or scene management.…