Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add slbug/claude-ruby-grape-rails/plugin install 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/skill-discovery-report)<a href="https://agentmods.dev/skills/slbug/claude-ruby-grape-rails/skill-discovery-report"><img src="https://agentmods.dev/badge/skills/slbug/claude-ruby-grape-rails/skill-discovery-report/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/skills/slbug/claude-ruby-grape-rails/skill-discovery-report"><img src="https://agentmods.dev/badge/skills/slbug/claude-ruby-grape-rails/skill-discovery-report.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 | $0.00088 | $0.00717 |
| Opus 5.5 | $0.00035 | $0.00287 |
| Sonnet 5.5 | $0.00018 | $0.00143 |
| Haiku 4.5 | $0.00009 | $0.00072 |
Grade A, and why
rb:discovery-report 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 1mo 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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill-Discovery Telemetry Report
Draft a redacted, actionable report from the opt-in skill-discovery
telemetry log. The log is generated by
hooks/scripts/skill-discovery-observer.rb when
RUBY_PLUGIN_DISCOVERY_LOG=1 is set in the user's environment.
Iron Laws
- Never auto-publish the report.
- Never delete user telemetry without an explicit request.
- Never include redacted prompt content verbatim in the drafted report.
- Quote a raw
excerptfield only when needed to explain a single match. - Never embed
rm,git reset, or other destructive command strings inside the drafted report — describe cleanup paths in prose only. - Treat trigger-table tweak suggestions as proposals; never auto-edit
${CLAUDE_PLUGIN_ROOT}/references/discovery/triggers.yml.
Workflow
- Run
${CLAUDE_PLUGIN_ROOT}/bin/discovery-stats --redact --jsonto dump the aggregate. - Inspect per-rule match counts + per-skill suggestion counts + per-event-kind volume.
- Identify high-frequency rules that match noise (overtrigger) — propose tightening their pattern.
- Identify low-frequency rules that miss real signal heuristically (e.g., rule fires on
<5%of relevant hook events) — propose loosening. - Draft a report to
.claude/audit/discovery/{datesuffix}.md.
Privacy posture
Redactor strips: prompt text beyond first 200 chars (EXCERPT_MAX_CHARS),
/Users/<name> paths, /home/<name> paths, uppercase KEY=value
env-style tokens. The --redact flag drops excerpt fields entirely from
the output.
Suggested rule tweaks
For each rule, classify:
- Overtrigger — rule fires very often but rarely points the user toward
/rb:<skill>. Propose tightening pattern or raisingconfidence_min. - Undertrigger — rule fires rarely, even when neighbor evidence suggests the skill is relevant. Propose loosening pattern or adding extractor.
- Stable — rule fires at a moderate, useful rate. Keep as-is.
Document each proposal with: rule id, current pattern, proposed pattern, supporting telemetry counts.
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.
- 1mo ago First seen · 61 lines · 88 tokens per session scan A 886f0531dd84
rb:discovery-report is a skill published in the GitHub repository slbug/claude-ruby-grape-rails (7 stars, last pushed 16d ago), licensed MIT. It adds 88 tokens to every session and 717 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-09-03.
Other skills, from other repositories
omh-rust
This is an OMH rust workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
redteam-web-detail-pack
Routing and boundary guidance for authorized general web application security testing. Use as a web testing router when the attack surface should be dispatched to more specific web vulnerability skills.
android-pentest
A guide for authorized security testing of Android apps, covering APK inspection, runtime testing, traffic capture, code review, and function hooking. An APK is the installable package used by an Android app.
manage-schemas
Creates, views, edits, deletes, and validates note schemas for the MCP Task Orchestrator in .taskorchestrator/config.yaml — the templates that define which notes agents must fill at each workflow phase. Also recommends schema designs from a library of workflow patterns (autonomous coding loops, spec-driven teams…
lighting-report-extract
Check reported lighting quantities and results in supplied simulation PDFs without adding repeated calculation surfaces. Use for scoped luminaire inventories and illuminance results; not simulation or compliance.