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 bks-lab/open-bridge --skill onboard-simgit clone --depth 1 https://github.com/bks-lab/open-bridgeWrote 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/bks-lab/open-bridge/onboard-sim)<a href="https://agentmods.dev/skills/bks-lab/open-bridge/onboard-sim"><img src="https://agentmods.dev/badge/skills/bks-lab/open-bridge/onboard-sim.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 5.1 | $0.00219 | $0.01242 |
| Opus 5 | $0.00110 | $0.00621 |
| Sonnet 5 | $0.00044 | $0.00248 |
| Haiku 4.5 | $0.00022 | $0.00124 |
Grade C, and why
onboard-sim 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 7d 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.
4. **Teardown** — `rm -rf <sandbox-dir>` (the sandbox is a throwaway temp tree). How it starts
The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
onboard-sim — adversarial onboarding-safety simulation
Proves an invariant the unit test can't: a realistic naive first-time-user
session, walking the real onboarding → commit → push path, cannot leak private
data to a public upstream. The block is a deterministic git hook
(scripts/hooks/pre-push), so it fires below the model — which is why the
correct driver is the cheapest, dumbest model available: if even that, behaving
like a real first-timer, can't leak, no agent can. Cost and speed are the bonus;
the model-independence is the actual claim.
Why a simulation (not just the unit test)
scripts/tests/test-push-guard.sh checks the hook's block/allow/bypass contract
in isolation. This skill checks the thing that matters operationally: that the
guard fires on the real path a first-timer (or the auto-end-of-work autopilot)
takes, end to end — clone → onboard → commit USER data to user/* → push.
Leak-safe by construction
The sandbox's "public upstream" is a local bare repo. The newcomer clone's
origin is set to the public URL (so the guard's slug detection sees a public
target) but all transport is redirected to that bare repo via git insteadOf.
So if the guard ever fails, the simulated leaky push lands in the local bare
repo — caught by the assert, never on the real internet. Testing for a leak
cannot cause one.
How it runs (4 phases)
-
Build —
assets/build-sandbox.sh <open-bridge-checkout> [sandbox-dir]prints the sandbox dir. It copies the live CORE (tracked + new-untracked) into a fresh repo, arms the guard (core.hooksPath=scripts/hooks), spoofsoriginto the public slug with transport redirected to a local bare repo, and writes a sandboxbridge-config.yamlso the guard recognizes the bare target as public. -
Drive the naive newcomer — two modes:
- Realistic (default): spawn ONE subagent via the Task tool with a cheap
model (
model: haiku), toolsBash, Read, Write, pointed at<sandbox>/newcomer, told to set up their identity + work and back it up to the remote — with an explicit "do not work around or disable any safety check" instruction (a naive user wouldn't). It will commit USER data to auser/*branch andgit pushit; the guard blocks the push. - Scripted (CI / no tokens):
assets/run-scripted-newcomer.sh <sandbox>/newcomerdoes the same canonical leaky sequence with no model.
- Realistic (default): spawn ONE subagent via the Task tool with a cheap
model (
What ships with it
3 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.
- 7d ago First seen · 94 lines · 219 tokens per session scan C 0bf3fb35c455
onboard-sim is a skill published in the GitHub repository bks-lab/open-bridge (8 stars, last pushed today), licensed MIT. It adds 219 tokens to every session and 1,242 once invoked, about $0.0011 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
laravel
Use when building or extending a Laravel 11/12 app — Eloquent models, migrations and relationships, routing with controllers and Form Requests, queues and background jobs, framework-native security (validation, mass-assignment, policies, signed URLs, rate limiting), and Pest/PHPUnit feature tests. NOT pure PHP…
thread-outbox-provider-push
Publish a fixture thread outbox entry through the Rust thread-outbox-provider front.
artisan-commands
Execute Laravel Artisan commands safely.
performant-php
High-performance modern PHP — PHP 8.4/8.5, OPcache+JIT, FrankenPHP workers, Composer, Symfony/Laravel, PHPStan/Psalm, Pest.
agency-filament-optimization-specialist
Expert in restructuring and optimizing Filament PHP admin interfaces for maximum usability and efficiency. Focuses on impactful structural changes — not just cosmetic tweaks.
laravel-specialist
Build and configure Laravel 10+ applications, including creating Eloquent models and relationships, implementing Sanctum authentication, configuring Horizon queues, designing RESTful APIs with API resources, and building reactive interfaces with Livewire. Use when creating Laravel models, setting up queue workers…