bridge-sync

bridge-sync is a skill for Claude Code, Codex from bks-lab/open-bridge. It costs 118 tokens per session (1,028 once invoked), scanned A, original, MIT.

An end-of-sprint workflow that sends all pending shared changes from a local branch to both configured upstream repositories. An upstream is the external repository you publish changes back to.

In plain words
What is it for?
Use it to publish pending core and organisation-level changes to open-bridge and its organisation overlay; use --repo to choose one destination or --dry-run to inspect the plan.
Why use it?
It removes the need to manually select and copy many commits after a sprint. It can also show the proposed routing first with a dry run and create pull requests for the destinations.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/bks-lab/open-bridge/bridge-sync
Any agent
npx skills add bks-lab/open-bridge --skill bridge-sync
Clone the repo
git clone --depth 1 https://github.com/bks-lab/open-bridge

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for bridge-sync

README.md
[![agentmods](https://agentmods.dev/badge/skills/bks-lab/open-bridge/bridge-sync.svg)](https://agentmods.dev/skills/bks-lab/open-bridge/bridge-sync)
Your own site
<a href="https://agentmods.dev/skills/bks-lab/open-bridge/bridge-sync"><img src="https://agentmods.dev/badge/skills/bks-lab/open-bridge/bridge-sync.svg" alt="Measured on agentmods" height="20"></a>
Per session 118 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,028 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00118 $0.01028
Opus 5 $0.00059 $0.00514
Sonnet 5 $0.00024 $0.00206
Haiku 4.5 $0.00012 $0.00103

Measured 4d ago against content hash 33b098705823, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

bridge-sync 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 4d 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.

skills/bridge-sync/SKILL.md · 93 lines

How it starts

The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Bridge Sync — Batch end-of-sprint upstream sync

/bridge-sync is the wide-net complement to /promote and /contribute.

Skill Granularity Use case
/promote per-commit "promote this batch of recent commits"
/contribute per-file "scan for upstream-worthy files, adapt, PR"
/bridge-sync per-sprint "push EVERYTHING pending to both upstreams now"

Read the referenced file ONLY when triggered.

When to use

  • End of a work-sprint, ready to publish all upstream-worthy changes at once
  • After a refactor that touched many CORE+org files — manual cherry-pick is tedious
  • When /promote has been deferred for days and there's a backlog
  • When you want both bks-lab/open-bridge and your org overlay updated in one operation

NOT for:

  • A single commit (/promote is leaner)
  • File-level adaptation work (/contribute --adapt does that)
  • USER-only changes (those stay local)

Arguments

Argument Effect Default
(none) Full sync to both upstreams
--dry-run Show routing matrix, don't push false
--repo open-bridge Sync only to open-bridge both
--repo <your-bridge> Sync only to your org overlay both
--since <ref> Sync commits since this ref (default: last sync tag) last sync
--no-scrub Disable open-bridge scrubbing (DANGER — only for emergency) false

Prerequisites

  • Current branch must be user/*. Refuses on development / main.
  • bridge-config.yaml.upstreams[] defines BOTH upstreams.
  • git remote has origin (your fork) + upstream (typically <your-org>/<your-bridge>).
  • For open-bridge sync: gh CLI authenticated with cross-fork PR rights.

Decision Tree

User wants to...
├── Full sync (default)                  → references/workflow.md
├── Dry-run / preview routing            → references/workflow.md (stop after Step 4)
├── Sync only one repo                   → references/workflow.md § --repo override
├── Configure scrub patterns             → rules/promote-safety.md per-repo blocklists
├── Tag the sync point                   → references/workflow.md § sync-tag
└── PR merge fails after squash-merge    → references/pr-recovery-patterns.md
    (stale-ancestor / non-fast-forward)

Read the full file on GitHub · 93 lines

Files

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.

Changes

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.

  1. 4d ago First seen · 93 lines · 118 tokens per session scan A 33b098705823

Subscribe to this mod's changes

bridge-sync is a skill published in the GitHub repository bks-lab/open-bridge (8 stars, last pushed 4d ago), licensed MIT. It adds 118 tokens to every session and 1,028 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.

Related

Other skills, from other repositories

kungfu-agent-onboarding

Use when a user asks to understand, start, inspect, extend, or safely operate installed Kungfu; verify the installed pack, select one intent route, personalize the explanation, and propose one smallest safe next action.

kungfu-systems/kungfu · 49 tokens

with-frontmatter

Help an agent inspect a failed trace run, identify likely failure layers, and produce a short audit note.

kungfu-systems/kungfu · 0 tokens

minimal

Help an agent inspect a failed trace run, identify likely failure layers, and produce a short audit note.

kungfu-systems/kungfu · 0 tokens

beevibe-team-mesh-negotiation

Multi-round negotiation protocol — covers both initiator and peer roles. Use when about to call negotiate(), when receiving a intent block as a peer, or when receiving an 'escalated' sentinel from a blocked respondnegotiate. Covers proposal crafting, counter-strategy, deadlock detection, when to accept early…

beevibe-ai/beevibe · 112 tokens

beevibe-verify-pr

CI verification before marking a PR-bearing task done. Use BEFORE calling mcpbeevibeupdateprogress(done) on any session whose deliverable is a pull request — including the first dispatch (you opened the PR with gh pr create) and any revision dispatch (you pushed new commits to an existing PR). Watches the PR's…

beevibe-ai/beevibe · 172 tokens

beevibe-use-repo

You are the child agent inside a fresh Docker sandbox. Borrow the given GitHub repo, produce a real artifact for the goal, and export it. Do not review the repo. The proof is that it works.

beevibe-ai/beevibe · 50 tokens