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-origin-safe-slash-overridegit 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-origin-safe-slash-override)<a href="https://agentmods.dev/skills/ychampion/cskill-agents/bridge-origin-safe-slash-override"><img src="https://agentmods.dev/badge/skills/ychampion/cskill-agents/bridge-origin-safe-slash-override/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-origin-safe-slash-override"><img src="https://agentmods.dev/badge/skills/ychampion/cskill-agents/bridge-origin-safe-slash-override.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 | $0.00036 | $0.00590 |
| Opus 5 | $0.00018 | $0.00295 |
| Sonnet 5 | $0.00007 | $0.00118 |
| Haiku 4.5 | $0.00004 | $0.00059 |
Grade A, and why
bridge-origin-safe-slash-override 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 11d 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 Origin Safe Slash Override
Domain: remote-input-safety Trigger: Apply when remotely delivered input should still default to plain-text slash handling, but a trusted bridge path needs to selectively re-enable only the slash commands that are safe to execute remotely. Source Pattern: Distilled from reviewed remote-control, bridge transport, and capability-advertising implementations.
Core Method
Keep remote slash-command parsing disabled by default for bridge-delivered input. If a remote message starts with /, inspect it locally first and resolve whether it maps to a known command. Re-enable slash handling only when the resolved command is explicitly bridge-safe; otherwise, intercept unsafe known commands with a friendly local denial and leave unknown slash text as plain text. This preserves the defensive default while still allowing a narrow, reviewed remote command surface.
Key Rules
- Preserve the “treat slash text as plain text” default at enqueue time so every other fast path still sees the defensive baseline.
- Reopen slash handling only after all three checks pass: the message is bridge-originated, starts with
/, and resolves to a command that passes bridge-safety filtering. - Treat known unsafe commands, especially local-jsx or terminal-only ones, as a local UX case rather than a model prompt: return a friendly denial such as "config isn't available over Remote Control." and stop before querying.
- Let unknown or malformed slash text fall through as plain text rather than converting it into a new local error surface for remote users.
- Keep discovery aligned with execution by advertising only bridge-safe commands to remote clients whenever possible; the override should narrow execution, not widen the visible command set.
Example Application
A mobile bridge sends /deploy-docs. The bridge layer parses it locally, confirms it is on the remote-safe allowlist, and then hands it to normal slash-command execution. The same bridge sends /config; the command resolves but is not remote-safe, so the system responds locally with a denial message. If the bridge sends /shrug and that text does not resolve to a known command, it stays plain text and is handled like an ordinary message.
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.
- 11d ago First seen · 30 lines · 36 tokens per session scan A a7a5e0bb7426
bridge-origin-safe-slash-override is a skill published in the GitHub repository ychampion/cskill-agents (36 stars, last pushed 5mo ago), licensed MIT. It adds 36 tokens to every session and 590 once invoked, about $0.0002 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 2026-08-30.
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.
review
Validate plans, execution, or PRs against wish criteria — returns SHIP / FIX-FIRST / BLOCKED with severity-tagged gaps.
work
Execute an approved wish plan — orchestrate subagents per task group with fix loops, validation, and review handoff.
brainstorm
Explore ambiguous or early-stage ideas interactively — tracks wish-readiness and crystallizes into a design for wish.
genie
Entry point for Genie operations — routes bug reports, questions, and operational commands, resumes existing lifecycle state, and orchestrates work that needs durable planning or coordination. Other ordinary requests bypass the lifecycle with a one-line notice unless the user asks for Genie.
wish
Convert an idea into a structured wish plan with scope, acceptance criteria, and execution groups for work.