agentsclimarketplace

Bridge safe command advertising

Skill ychampion/cskill-agents/agents/codex/skills/bridge-safe-command-advertising

Agent skills for coding CLIs, multi-agent runtimes, context engines, MCP extensions, and terminal tooling. Instead of using claude code's source code, give your agent skills to create your own!

Install
npx -y skills add ychampion/cskill-agents --skill bridge-safe-command-advertising

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

What its author says it does

Copied from the file, not written here

Advertise only slash commands that a bridge client can actually invoke by filtering announcements with the same bridge-safety predicate used at execution time.

SKILL.md

2.7 KB, 458 tokens by cl100k_base, as published. Nobody here has run it

SKILL: Bridge Safe Command Advertising

Domain: command-architecture Trigger: Use when a bridged or remote client receives an announced slash-command list and that list must stay aligned with the commands the runtime will actually execute for bridge-originated input. Source Pattern: Distilled from reviewed remote-control, bridge transport, and capability-advertising implementations.

Core Method

Filter the command list before serializing any remote capability announcement, and filter it with the exact same bridge-safety predicate the runtime will use when the remote client later invokes a slash command. Let the shared serializer keep its generic user-invocable check, but pass it a prefiltered list that already excludes bridge-unsafe commands. This keeps the announced surface honest: every command the client sees is one the bridge path can actually execute, and every command the bridge path rejects stays undiscoverable instead of becoming a guaranteed dead end.

Key Rules

  • Reuse the runtime bridge-safety predicate at announcement time instead of inventing a second listing-only filter.
  • Apply the bridge-safe filter before generic serializers flatten commands into plain names; once only names remain, execution-policy drift is harder to spot and correct.
  • Keep shared message builders transport-agnostic: they may still filter out non-user-invocable entries, but transport-specific safety should be decided by the caller that owns that transport.
  • Treat advertised command lists as part of the execution contract, not as best-effort discoverability metadata.
  • When bridge execution rules change, update the shared predicate so announcement and invocation stay synchronized automatically.

Example Application

When a CLI session opens a phone companion over a bridge and emits system init, filter the command registry through is bridge safe command before calling the generic init-message builder. The serialized slash_commands list then includes summary and compact, but omits local-only UI commands such as model that the bridge path would reject later.

Anti-Patterns (What NOT to do)

  • Do not advertise every user-invocable command and rely on runtime failures to teach remote clients what is unsupported.
  • Do not maintain a separate announcement-only allowlist that can drift away from the real bridge execution gate.
  • Do not hide transport-specific safety inside the generic serializer when different callers may need different execution contracts.

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Gives 0 of the 12 instructions most marketing audience skills give in 458 tokens

Counted across 690 of the 894 authors here whose files we hold, read 2026-08-07

  • Apply Poppins font to headingsin 41 of 690, across 6 files
  • Apply Lora font to body textin 41 of 690, across 6 files
  • Use Arial fallback for headingsin 39 of 690, across 4 files
  • Use Georgia fallback for body textin 39 of 690, across 4 files
  • Maintain text hierarchy and formattingin 39 of 690, across 4 files
  • Use accent colors for non-text shapesin 38 of 690, across 3 files
  • Use RGB values for precise color matchingin 38 of 690, across 3 files
  • Use brand colors for primary text and backgroundsin 36 of 690, across 1 file
  • Read product marketing context file before asking questions, starting, or auditingin 35 of 690, across 23 files
  • Use active voice instead of passive voicein 26 of 690, across 10 files
  • Implement or generate appropriate JSON-LD structured datain 24 of 690, across 17 files
  • Prioritize clarity over clevernessin 22 of 690, across 8 files

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

Keep looking

Skills are one crate of 327,132. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.