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 bsbofmusic/codexpro-bridge --skill codexpro-bridge-routergit clone --depth 1 https://github.com/bsbofmusic/codexpro-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/bsbofmusic/codexpro-bridge/codexpro-bridge-router)<a href="https://agentmods.dev/skills/bsbofmusic/codexpro-bridge/codexpro-bridge-router"><img src="https://agentmods.dev/badge/skills/bsbofmusic/codexpro-bridge/codexpro-bridge-router/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/bsbofmusic/codexpro-bridge/codexpro-bridge-router"><img src="https://agentmods.dev/badge/skills/bsbofmusic/codexpro-bridge/codexpro-bridge-router.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 | $0.00051 | $0.00568 |
| Opus 5 | $0.00026 | $0.00284 |
| Sonnet 5 | $0.00010 | $0.00114 |
| Haiku 4.5 | $0.00005 | $0.00057 |
Grade A, and why
codexpro-bridge-router 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 today.
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.
What it actually says
CodexPro Bridge Router
Use Bridge with progressive disclosure: keep the default path short and expand only when the task needs another capability.
For non-trivial work, call codexpro_bridge_route_and_recall first. For a new standalone task, normally set memory off; enable recall when the user asks to continue, recover, compare with, or reuse prior context. A memory lookup never depends on a Skill name matching the query.
Choose the best managed PRIMARY Skill and call codexpro_bridge_load_skill before acting. Load only that Skill first; add one SECONDARY only when the task genuinely crosses owners. Load referenced resources only when the selected Skill or task requires them.
Use Bridge capabilities only on demand:
- Memory — use
codexpro_bridge_memory_searchor the direct memory list/call tools when the task explicitly depends on prior sessions or shared-memory content. Do not search memory for every new task. - Work — use
codexpro_bridge_workwhen lifecycle state has value: explicit TODO execution, multi-step durable work, checkpoint/resume, project context, mechanical audit, artifact tracking, completion tracking, or prompts such as “列 TODO / 逐项做 / 做完 / 机械审计 / 继续未完成任务”. Do not create Work state for ordinary one-shot answers. - MCP — use
codexpro_bridge_mcp_list/codexpro_bridge_mcp_callonly when the task or selected Skill needs an external shared capability. Query narrowly and invoke the exact tool; do not enumerate the full AgentGateway catalog by default.
Work records state and evidence; it is not an executor. Use the separate CodexPro connection for VPS files, Bash, Git, repository inspection, tests, deployments, and writes. External-system actions stay with the corresponding upstream MCP. After real execution, write concise outcomes and mechanical evidence back to Work. If a final Work audit is required, freeze material task/step state before creating the audit so PASS stays bound to the current revision.
Bridge does not own Skill or MCP state, and it does not own memory state; Skills Manager, AgentGateway, Obsidian and MemOS remain authoritative. Never mirror their catalogs into a second index or add a hidden scheduler/router just to automate these usage rules.
For ordinary chat, short calculations, rewrites, or questions already answerable from the current conversation, skip Bridge routing and extra state. Never replay an upstream operation after a delivery-unknown result.
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.
- today Changed · -4 lines · -14 tokens per session f145de3668db
- 9d ago First seen · 29 lines · 65 tokens per session scan A 62152c9422f1
codexpro-bridge-router is a skill published in the GitHub repository bsbofmusic/codexpro-bridge (0 stars, last pushed today), licensed MIT. It adds 51 tokens to every session and 568 once invoked, about $0.0003 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…