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 jschulte/claude-plugins --skill bulletproofgit clone --depth 1 https://github.com/jschulte/claude-pluginsWrote 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/jschulte/claude-plugins/bulletproof)<a href="https://agentmods.dev/skills/jschulte/claude-plugins/bulletproof"><img src="https://agentmods.dev/badge/skills/jschulte/claude-plugins/bulletproof/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/jschulte/claude-plugins/bulletproof"><img src="https://agentmods.dev/badge/skills/jschulte/claude-plugins/bulletproof.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 | $0.00045 | $0.01969 |
| Opus 5.5 | $0.00018 | $0.00788 |
| Sonnet 5.5 | $0.00009 | $0.00394 |
| Haiku 4.5 | $0.00005 | $0.00197 |
Grade A, and why
bulletproof 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 24d 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 — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bulletproof Pre-Ship Review
Overview
Produce an honest, evidence-backed release verdict. Passing checks are supporting evidence; the core job is to determine whether the changed system still preserves its contracts across real user, data, provider, and recovery paths.
Core principle: review the failure semantics before selecting gates. Never turn a review request into unauthorized implementation or release work.
Choose the operating mode
Infer only what the user actually authorized. When unclear, use audit-only.
| Mode | Allowed work | Not implied |
|---|---|---|
| Audit-only (default) | Inspect code, PR state, history, CI, and docs; fetch remote refs; run safe diagnostic checks; use disposable local resources | Source edits, test creation, commits, pushes, PR comments, issue changes, merge, deploy |
| Audit-and-fix | Audit plus the specifically authorized code/test changes and local verification | Push, PR mutation, merge, deploy |
| Release execution | Only the external mutations the user explicitly requested | Any adjacent publication, rollout, or cleanup |
Updating a remote branch is a separate mutation. If requested, determine whether the user means local integration or the remote PR branch. Record the remote SHA before the update, use the repository's accepted merge/rebase policy without rewriting history unless explicitly authorized, and verify the final remote SHA and ancestry. Do not treat “review,” “ship,” or “bulletproof” alone as permission to push.
In audit-only mode, continue gathering independent findings after discovering a blocker. Do not “stop and fix,” create regression tests, save reports in the repository, or edit the PR.
Establish the exact review state
- Read the applicable instruction hierarchy and project release/migration/runbook documents. Do not assume a particular instruction filename, package manager, runtime, framework, base branch, or CI system.
- Resolve the PR's actual base and head from current remote evidence. Record base SHA, head SHA, merge base, divergence, worktree status, and whether required checks belong to that exact head.
- Preserve user work. If the checkout is dirty, or a command may write caches, generated files, dependencies, databases, or build output, use an isolated worktree or other disposable environment. Never stash, switch, clean, or delete caches in the user's active dirty checkout.
- If a base update was authorized, perform it before the substantive review. Report before/after SHAs, integration method, conflicts, push status, and final ancestry. Substantive conflict resolution is code authorship; do it only when authorized.
- Review the post-integration diff. Distinguish the code reviewed, remote CI, merge state, deployment, and live behavior; none proves the others.
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.
- 24d ago First seen · 138 lines · 45 tokens per session scan A f701b1e200ee
bulletproof is a skill published in the GitHub repository jschulte/claude-plugins (0 stars, last pushed 25d ago), licensed MIT. It adds 45 tokens to every session and 1,969 once invoked, about $0.0002 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 2026-10-12.
Other skills, from other repositories
github-automation
GitHub workflow automation, PR management, issue tracking, and code review coordination. Integrates with GitHub Actions and repository management. Use when: PR creation, code review, issue management, release automation, workflow setup. Skip when: local-only changes, non-GitHub repositories.
github
GitHub via gh CLI: PRs, issues, reviews, repos, auth.
otto-drive-pr
PR mergeability, CI, and live preview.
voicestudio-maintainer
Triage GitHub issues, review contributor pull requests, diagnose CI, and prepare explicitly requested releases for VoiceStudio's Electron desktop app and Python backend. Use for repository maintenance work, not ordinary VoiceStudio audio generation.
release
Cut a brooks-lint release: set the version in package.json, propagate it across all four plugin manifests and every version-bearing text file (README badges, docs site metadata), write the CHANGELOG entry, validate, then commit, push, tag, and publish the GitHub release. Triggers when the maintainer asks to "release"…
release-pr-review
Review pass on an open release PR (release/ → main) — the step between git-wrapup and release-and-publish when a project releases in gated release PR mode. Reads the PR's commit range through the code-simplifier lens plus a correctness review, verifies whatever an automated reviewer left on the PR, lands fixes as…