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/bitovi/convey/mode-button-behaviornpx skills add bitovi/convey --skill mode-button-behaviorgit clone --depth 1 https://github.com/bitovi/conveyWhat 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 | $0.00056 | $0.05696 |
| Opus 5 | $0.00028 | $0.02848 |
| Sonnet 5 | $0.00011 | $0.01139 |
| Haiku 4.5 | $0.00006 | $0.00570 |
Grade A, and why
mode-button-behavior 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 3d 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 — 360 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mode & Component Button Behavior
Purpose
This skill documents the complete interaction flows for the global mode buttons and component row buttons. These two button systems work together but have independent state.
Before modifying any button behavior, tab visibility, or page interaction logic:
- Review the flow tables below
- Identify which flow(s) your change affects
- Update the tables to reflect the proposed new behavior
- Confirm the updated tables with the user
- Only then implement the change
Key Concepts
There are three button systems that stay in sync:
- Panel mode buttons (top-left of panel): Select and Insert. These control which tab is visible AND whether the page has an active interaction (crosshair, hover outlines, browse indicators).
- Overlay toolbar buttons (floating bar on the page, above selected element): Select, Insert, Design, Text, Replace, Place. These mirror the panel's mode and tab state. Clicking a button on either side syncs the other via WebSocket.
- Component row buttons (inside the Place/Replace tab): One per component. These arm a specific component for placement or replacement.
The panel and overlay toolbars stay in sync bidirectionally:
- Clicking a mode/tab button on the panel sends a message to the overlay, which rebuilds its toolbar to match.
- Clicking a mode/tab button on the overlay sends a message to the panel, which updates its state to match.
- The same state transitions apply regardless of which side the user clicks.
The panel mode buttons and overlay mode buttons do two orthogonal things that happen to be bundled together:
- Show a tab — make the Place or Replace tab visible so the user sees the component list
- Activate a page interaction — turn on the overlay's browse/crosshair mode
After a component is placed or replaced, the tab should stay visible but all page interactions stop and both buttons return to gray.
Button Colors
Panel mode buttons (Select, Insert)
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.
- 3d ago First seen · 360 lines · 56 tokens per session scan A 27c4230ed9b9
mode-button-behavior is a skill published in the GitHub repository bitovi/convey (46 stars, last pushed 17d ago), licensed MIT. It adds 56 tokens to every session and 5,696 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 2026-08-30.
Other skills, from other repositories
opencli-sitemap-author
Use when creating or maintaining OpenCLI site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge for a website. Use after browser exploration discovers durable site context, when a sitemap is stale, or when promoting local site knowledge into the repo.
golden-rss
Use when testing the rss golden build.
omh-buzz
This is a Hermes-native buzz workflow skill.
redteam-api-detail-pack
Domain routing and boundary guidance for authorized API security testing, including BOLA/IDOR, authentication bypass, mass assignment, missing rate limits, and GraphQL issues. Use when a task belongs to the API testing domain and needs scope, evidence, pivot, or exit criteria.
redteam-postex-detail-pack
Domain routing and boundary guidance for authorized post-exploitation testing after initial access, including privilege escalation, persistence, lateral movement, data collection, and cleanup considerations. Use when a task belongs to the post-exploitation domain and needs scope, evidence, pivot, or exit criteria.
android-pentest
安卓应用渗透测试 — APK分析、Hook、自动化测试、运行态驱动、签名恢复、抓包分析.