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/plugin-dev-workflownpx skills add slbug/claude-ruby-grape-rails --skill plugin-dev-workflowgit clone --depth 1 https://github.com/slbug/claude-ruby-grape-railsWhat 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 | $0.00040 | $0.01056 |
| Opus 5 | $0.00020 | $0.00528 |
| Sonnet 5 | $0.00008 | $0.00211 |
| Haiku 4.5 | $0.00004 | $0.00106 |
Grade C, and why
plugin-dev-workflow scanned grade C with 1 finding 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 2d 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
- `rm -rf` only for validated `mktemp -d` outputs; prefer `rmdir` for expected-empty lock dirs How it starts
The opening of the file, as written. The whole thing — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plugin Development Workflow
Audience: Agents, Not Humans
Imperative-only. Tables for command/option lists.
Verification ordering
Run deterministic gates before drawing conclusions from session
analytics. See .claude/rules/development.md § "Deterministic-First
Ordering".
Surface Boundary
Two surfaces, kept separate in implementation + validation:
| Surface | Path |
|---|---|
| shipped plugin | plugins/ruby-grape-rails/ |
| contributor-only tooling | .claude/ |
Supported environments: macOS, Linux, WSL. Native Windows: NOT supported.
Session analytics under .claude/skills/session-* and
.claude/skills/skill-monitor/: exploratory only, NOT release-grade.
Scope Check
Before editing, identify the surface:
| Layer | Files |
|---|---|
| shipped plugin | skills, agents, hooks, bin/, plugin settings.json, plugin metadata, README, user-facing docs |
| contributor tooling | .claude/skills/, .claude/agents/, local planning/audit notes |
Do NOT treat contributor-only changes as shipped plugin features.
Validation Matrix
Run checks matching the files touched:
| Files touched | Run |
|---|---|
| Markdown docs / skills / agents | npx markdownlint <touched-files> |
| Shell hooks | bash -n plugins/ruby-grape-rails/hooks/scripts/FILE_NAME.sh, shellcheck -x plugins/ruby-grape-rails/hooks/scripts/FILE_NAME.sh |
bin/ executables |
bash -n plugins/ruby-grape-rails/bin/BIN_NAME, shellcheck plugins/ruby-grape-rails/bin/BIN_NAME, mock-test via crafted stdin when the executable reads hook-style JSON |
| Ruby scripts | ruby -c FILE_PATH |
| Shipped plugin shape | claude plugin validate --strict plugins/ruby-grape-rails |
| Marketplace manifest | claude plugin validate --strict . (not covered by the plugin-directory run) |
Contributor components under .claude/ |
claude plugin validate --strict .claude (bare component directory; reports SKILL.md frontmatter that fails to parse) |
| Contributor eval tooling | make eval, make eval-all, make eval-ci-deterministic, make eval-output, make security-injection, make eval-tests, make eval-overlap, make eval-hard-corpus |
What ships with it
1 file 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.
- 2d ago First seen · 114 lines · 40 tokens per session scan C 22ad2a76df71
plugin-dev-workflow is a skill published in the GitHub repository slbug/claude-ruby-grape-rails (7 stars, last pushed 2d ago), licensed MIT. It adds 40 tokens to every session and 1,056 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
opencli-sitemap-author
Use when creating or maintaining OpenCLI site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge for a website. Use after browser exploration discovers durable site context, when a sitemap is stale, or when promoting local site knowledge into the repo.
golden-rss
Use when testing the rss golden build.
omh-code-review
This is a Hermes-native code-review workflow skill.
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
安卓应用渗透测试 — APK分析、Hook、自动化测试、运行态驱动、签名恢复、抓包分析.
studio
Architecture Studio control plane — initialize or inspect a studio workspace, create and register projects, or route an architecture/AEC task to the right agent or skill. Use when the user runs /as:studio, asks to set up or open their studio, manage its projects, or describes a task without naming a skill.