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/kadaba/claude-bridge/bridge-pushnpx skills add kadaba/claude-bridge --skill bridge-pushgit clone --depth 1 https://github.com/kadaba/claude-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/kadaba/claude-bridge/bridge-push)<a href="https://agentmods.dev/skills/kadaba/claude-bridge/bridge-push"><img src="https://agentmods.dev/badge/skills/kadaba/claude-bridge/bridge-push.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 | $0.00126 | $0.01764 |
| Opus 5 | $0.00063 | $0.00882 |
| Sonnet 5 | $0.00025 | $0.00353 |
| Haiku 4.5 | $0.00013 | $0.00176 |
Grade A, and why
bridge-push 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 5d 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 — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
bridge-push (hybrid)
Move files to the VPS with a spoken handshake. Coordination rides Claude's
built-in Remote Control (ListAgents + SendMessage) — no relay, no SSH tunnel
for the talking. The bytes ride a real transport that preserves them
exactly: git (preferred) or rsync/tar over SSH. Both ends verify a manifest.
Why not send files over SendMessage? That channel carries text through an LLM, so exact bytes aren't guaranteed. Inline only tiny text files, and only with a sha check (see "Inline escape hatch"). For a real folder, use git or rsync.
Transport-agnostic helpers in scripts/:
bridge-transfer.sh <src> <ssh_host> <dest> [--delete]→ the atomic byte-path: opens ONE ssh connection, transfers, verifies every file's checksum on the VPS, then closes the connection. Exit 0 = VERIFIED, 1 = MISMATCH. Prefer this.bridge-manifest.sh <path>→FILES/BYTES/SHAfingerprint (for manual checks).bridge-push.sh <src> <ssh_host> <dest> [method] [--delete]→ transfer only, no verify.bridge-recv-prep.sh <dest>→ VPS: create dest, report free space + readiness.
Preconditions (check once)
- Find the peer:
ListAgents. Identify the VPS session (ask the user which one if the name isn't obvious, e.g.vps-myapp). Note its name/id. - Is it online? Remote Control sessions show
offlinewhen not connected. If offline → tell the user to open/connect the VPS Claude session (Remote Control on). Do NOT proceed blind. (If it must work offline, fall back to the bridge relay — see "Offline fallback".) - Byte transport available? Prefer git if the app is a repo both can reach.
Else confirm
ssh <alias> trueworks from local for rsync.
Shared journal (MCP)
If the journal MCP server is registered, use it as the source of truth:
journal_read() at the start, claim(who, "push:<dest>") before transferring
(so two pushes don't collide), journal_log(who, "PUSH", "<name>@<sha>", "VERIFIED")
after a verified transfer, then release. who is your identity (local/vps).
What ships with it
4 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.
- 5d ago First seen · 105 lines · 126 tokens per session scan A 29c7db085369
bridge-push is a skill published in the GitHub repository kadaba/claude-bridge (3 stars, last pushed 21d ago), licensed MIT. It adds 126 tokens to every session and 1,764 once invoked, about $0.0006 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 2026-08-31.
Other skills, from other repositories
event-driven-architecture
Kafka, RabbitMQ, SQS/SNS, event sourcing, CQRS, saga patterns, dead letter queues, and idempotency. Use when designing asynchronous systems, implementing message-driven workflows, or building event streaming pipelines.
devops-cloud
DevOps, cloud infrastructure, and platform engineering. Use when working with AWS, GCP, Azure, Kubernetes, Terraform, CI/CD pipelines, or infrastructure as code.
edge-computing
Edge computing with Cloudflare Workers, Deno Deploy, Bun, Vercel Edge Functions, AWS Lambda@Edge, and edge databases (Turso, D1, DynamoDB Global Tables). Use when building low-latency edge applications, edge-side rendering, or globally distributed compute.
conducting-cloud-incident-response
Responds to security incidents in cloud environments (AWS, Azure, GCP) by performing identity-based containment, cloud-native log analysis, resource isolation, and forensic evidence acquisition adapted for ephemeral cloud infrastructure. Activates for requests involving cloud incident response, AWS security incident…
managing-cloud-identity-with-okta
This skill covers implementing Okta as a centralized identity provider for cloud environments, configuring SSO integration with AWS, Azure, and GCP, deploying phishing- resistant MFA with Okta FastPass, managing lifecycle automation for user provisioning and deprovisioning, and enforcing adaptive access policies based…
hunt-cache-poison
Hunting skill for cache poison vulnerabilities. Built from 4 public bug bounty reports. Use when hunting cache poison on any target.