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 ychampion/cskill-agents --skill bridge-safe-command-advertisinggit clone --depth 1 https://github.com/ychampion/cskill-agentsWrote 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/ychampion/cskill-agents/bridge-safe-command-advertising)<a href="https://agentmods.dev/skills/ychampion/cskill-agents/bridge-safe-command-advertising"><img src="https://agentmods.dev/badge/skills/ychampion/cskill-agents/bridge-safe-command-advertising/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/ychampion/cskill-agents/bridge-safe-command-advertising"><img src="https://agentmods.dev/badge/skills/ychampion/cskill-agents/bridge-safe-command-advertising.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 | $0.00034 | $0.00508 |
| Opus 5.5 | $0.00014 | $0.00203 |
| Sonnet 5.5 | $0.00007 | $0.00102 |
| Haiku 4.5 | $0.00003 | $0.00051 |
Grade A, and why
bridge-safe-command-advertising 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 1mo 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 — 30 lines — stays where its author put it; the contents beside it link to each section on GitHub.
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.
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.
- 1mo ago First seen · 30 lines · 34 tokens per session scan A 56d04a9b9dca
bridge-safe-command-advertising is a skill published in the GitHub repository ychampion/cskill-agents (36 stars, last pushed 6mo ago), licensed MIT. It adds 34 tokens to every session and 508 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-08-30.
Other skills, from other repositories
grape
Use Grape MCP for Codex context continuity in coding repositories. Use when a task needs repeated-turn context, omitted context restore, stale-context checks, invalidation checks, or safe continuity across branch and dirty-worktree changes.
gh
GitHub CLI skill for interacting with GitHub via the gh command line tool. Use when Bub needs to (1) Create, view, or manage GitHub repositories, (2) Work with issues and pull requests, (3) Create and manage releases, (4) Run and monitor GitHub Actions workflows, (5) Create and manage gists, (6) Install and manage…
brain-ingest
The process for digesting a conversation, document, or research result, classifying it, and writing it down as brain content (a root-page update or a new/updated page) through the brain CLI.
wish
Deliver one decided task end to end — admit it, work it in one worktree, gate, independent review, bounded repair, a merge-ready PR — or plan a multi-group wish when it is bigger than one task.
gate-control
Canonical VideoStudio review authorization and state-transition policy. Use after any Gate B/C/Preview/D decision, post-gate revision, resumed approval, or exhausted visual-QA result across COMPOSE/AUTO/GENERATE/EDIT; maps explicit user authority and durable artifact state to one next action with ovs gate transition.…
report
Investigate a failure to its root cause with grounded evidence, hand the diagnosis to fix, and create a GitHub issue only when asked.