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 skills add aliengiraffe/vigilante --skill vigilante-issue-implementation-on-rubygit clone --depth 1 https://github.com/aliengiraffe/vigilanteWrote 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/aliengiraffe/vigilante/vigilante-issue-implementation-on-ruby)<a href="https://agentmods.dev/skills/aliengiraffe/vigilante/vigilante-issue-implementation-on-ruby"><img src="https://agentmods.dev/badge/skills/aliengiraffe/vigilante/vigilante-issue-implementation-on-ruby.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00041 | $0.00785 |
| Opus 5 | $0.00020 | $0.00392 |
| Sonnet 5 | $0.00008 | $0.00157 |
| Haiku 4.5 | $0.00004 | $0.00078 |
Grade A, and why
vigilante-issue-implementation-on-ruby 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 8d 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 — 37 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Vigilante Ruby Issue Implementation
Focus
- Read the prompt for detected tech stacks, Ruby process hints, and Ruby security guidance before changing code.
- Prefer repository-defined Ruby workflows over guessed framework defaults.
- Keep changes scoped to the issue and do not broaden into unrelated lint, dependency, or style cleanup.
Ruby Tooling Workflow
- Bundler: run Ruby tooling through Bundler-managed commands when the repository uses Bundler, such as
bundle exec <command>or documented binstubs. Respect the committed lockfile and avoid ad hoc gem execution outside the repo's dependency context. - Testing: start with the repository's standard test entrypoint for the touched area, such as
bundle exec rspec,bundle exec ruby -Itest,bundle exec rake test, Rails test tasks, or another documented command. Prefer targeted suites first, then widen only when needed. - Linting and style: use the repository's established lint or style tooling. When RuboCop is configured, run the repo-standard RuboCop command through Bundler. Do not introduce new lint tooling unless the issue specifically requires it.
- Dependency and security audits: run
bundle auditorbundler-auditwhen it is installed or already part of the repository workflow and the change touches dependencies or security-sensitive code. For Rails applications, run Brakeman when it is already configured or documented for the repo. If those tools are not present, note that and continue with the other validation paths. - Dependencies: keep
Gemfile.lockor other Bundler lockfiles in sync with dependency changes. Prefer minimal dependency churn and respect the repo's existing gem sources and update policy.
Ruby Secure Coding
- Avoid unsafe deserialization of untrusted data. Prefer safe formats and parser modes over
Marshal.load, unrestricted YAML loading, or similar dangerous object materialization paths. - Avoid shell injection by preferring APIs that accept explicit argv arrays and by validating or escaping untrusted input when shelling out is unavoidable.
- Do not store secrets, credentials, or tokens in source files, fixtures, seeds, or committed environment files.
- For Rails or Rack applications, preserve secure defaults around strong parameters, CSRF protections, escaping, and framework security configuration unless the issue explicitly requires changing them.
- Prefer current maintained gems and standard-library capabilities over custom security-sensitive code when the repository already has an established safe path.
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.
- 8d ago First seen · 37 lines · 41 tokens per session scan A 4d968a53d8e8
vigilante-issue-implementation-on-ruby is a skill published in the GitHub repository aliengiraffe/vigilante (39 stars, last pushed yesterday), licensed Apache-2.0. It adds 41 tokens to every session and 785 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 skills, from other repositories
pipeline-conductor
Operating procedure for the kirocrew-pipeline-conductor agent - run one issue/PR pipeline on one repository as a supervised fleet. Auto-pick items, preflight every candidate to one deterministic claim verdict, stand up one worker session per item in a dedicated folder, probe them each cycle with one script call…
release-notes
Draft a release note section from a commit range, grouped by what the reader gets.
shipping-a-pr
Use when finished work needs to ship as a pull request, or when the ask is about a PR — creating one, bringing it up to date, adding screenshots, watching its checks, or addressing its review comments. Not for reviewing a PR you are not shipping.
prepare-pr
End-to-end drives working-tree changes to a review-ready pull request — commit, sync base, squash to one commit, open/update the PR — then KEEPS RUNNING IN-SESSION (poll CI + code-review bots in 5-min rounds, up to 10) fixing every legitimate Critical/High finding and build failure until the PR is review-ready (never…
kirocrew-worktree-dev
HARD RULE for developing the Kiro Crew source repo ITSELF (not for users' own projects): every change is built and verified inside a git worktree, never against the live gateway. Covers worktree creation, the blocking local build gates (pytest + isort + flake8 + mypy + tsc + vitest), the built-dist gotcha, feature…
git-commit-helper
Generate conventional commit messages automatically. Use when user runs git commit, stages changes, or asks for commit message help. Analyzes git diff to create clear, descriptive conventional commit messages. Triggers on git commit, staged changes, commit message requests.