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 agentmods add skills/tentacleopera/switchboard/switchboard-contractsnpx skills add TentacleOpera/switchboard --skill switchboard-contractsgit clone --depth 1 https://github.com/TentacleOpera/switchboardWrote 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/tentacleopera/switchboard/switchboard-contracts)<a href="https://agentmods.dev/skills/tentacleopera/switchboard/switchboard-contracts"><img src="https://agentmods.dev/badge/skills/tentacleopera/switchboard/switchboard-contracts.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.02062 |
| Opus 5 | $0.00000 | $0.01031 |
| Sonnet 5 | $0.00000 | $0.00412 |
| Haiku 4.5 | $0.00000 | $0.00206 |
Grade A, and why
switchboard-contracts 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.
How it starts
The opening of the file, as written. The whole thing — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: Switchboard Contracts — Agent-Facing Behavior Reference
Scope. This is a behavior reference, not an invocation reference. It answers "how does Switchboard behave?" — never "how do I call endpoint X?" For invocation (endpoints, verbs, payload fields), read
.agents/protocols/switchboard-mission-control-http/SKILL.mdandGET /catalog. Consult this skill when you are unsure why something happens or what a system convention is. Every fact below cites its source-of-truth file so staleness is checkable; the contracts are slow-moving (conventions), not mechanics.
These are the behavioral contracts an agent driving Switchboard must know. They were extracted from source because the user manual targets human UI users ("click the button") and is useless to an agent — these facts had to be re-derived from source every time a managing agent needed them.
Contracts
-
Cards move on coding start; they never move on finish. The column move is the dispatch — moving a card to a coding column fires the agent prompt. There is no "move on completion" step. Completion is detected by a different mechanism (see #2). Source:
src/services/KanbanProvider.ts(dispatch branches persist the move and then build the prompt;// The move persists immediately and does not wait on dispatch.). -
Completion signal = first plan-file
mtimeadvance after dispatch. The activity light's OFF-switch fires when the plan file is edited afterdispatched_atis set. The dispatch flow does not write the plan file (it only runs SQL), so any mtime advance reaching the watcher whiledispatched_atis set is the agent's completion edit. No agent-authored text is trusted as a control signal — only the mtime advance. The mtime advance drives the activity light and the silence signal (the queue watch's idle input); it is no longer load-bearing for board progression — the completion-driven dispatch arm was deleted, and the next card is pulled by the lead, theRun queuebutton, or the schedule calling the queue pop. Source:src/services/GlobalPlanWatcherService.ts(activity-light OFF-switch comment +clearWorkingStateon edit whiledispatchedAtset).
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.
- 4d ago First seen · 128 lines · 0 tokens per session scan A f841cc1b4962
switchboard-contracts is a skill published in the GitHub repository TentacleOpera/switchboard (213 stars, last pushed 4d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,062 tokens. 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
wayfinder
Plan a huge chunk of work (more than one agent session can hold) as a shared map of decision tickets on your issue tracker, and resolve them one at a time until the way to the destination is clear.
sap-transport-overview
System-wide inventory of open transport requests — every visible modifiable request, who owns it, how big it is, and supported risk signals such as empty/local requests, explicit locks, and confirmed manifest overlaps. Headers-only and cheap; NO source diffs. Use when asked "what transports are open in the system"…
timeline-creator
Create HTML timelines and project roadmaps with Gantt charts, milestones, phase groupings, and progress indicators. Use when users request timelines, roadmaps, Gantt charts, project schedules, or milestone visualizations.
okx-task-watch
监听任务进展 / 帮我盯着任务 / 任务有动静告诉我 / 历史消息 / 未读消息 / 未决策 / 待决策 / 继续监听 / task watch / user watch / monitor task progress / catch me up on tasks / outstanding decisions — OKX A2A user-session task-notification monitor: live long-poll via okx-a2a user watch (also drains backlog of past/missed/unread events on entry) plus…
pm-all
Skill "pm-all" from wei63w/pm-manager, covering user input, outline and shared workflow (all /pm- commands).
bootstrap-prd
Set up PRD-driven development infrastructure for a new project, including directory structure, templates, and roadmap.