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 MathAndMagic/bridgeapp-plugin --skill bridgeapp-threadgit clone --depth 1 https://github.com/MathAndMagic/bridgeapp-pluginWrote 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/mathandmagic/bridgeapp-plugin/bridgeapp-thread)<a href="https://agentmods.dev/skills/mathandmagic/bridgeapp-plugin/bridgeapp-thread"><img src="https://agentmods.dev/badge/skills/mathandmagic/bridgeapp-plugin/bridgeapp-thread/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/mathandmagic/bridgeapp-plugin/bridgeapp-thread"><img src="https://agentmods.dev/badge/skills/mathandmagic/bridgeapp-plugin/bridgeapp-thread.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 | $0.00061 | $0.00487 |
| Opus 5.5 | $0.00024 | $0.00195 |
| Sonnet 5.5 | $0.00012 | $0.00097 |
| Haiku 4.5 | $0.00006 | $0.00049 |
Grade A, and why
bridgeapp-thread 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 2mo 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.
What it actually says
Reading a BridgeApp conversation
You were pointed at one message. Read the conversation around it before doing anything with it.
Read the whole thing, not the first page
list_thread_messages(thread_id) when the message has a thread
list_chat_messages(chat_id) when it does not
Both return 15 messages per page. Keep paging until a page comes back short or empty. Stopping at the first page is the single most common way to misread a BridgeApp conversation: the reply that matters is usually not in the first fifteen.
list_chat_messages takes created_after and created_before as RFC3339
timestamps. When you only need the neighbourhood of one message, bracket it
rather than reading the channel from its beginning.
Pick up what the agents did
A message with agent activity has a transcript: reasoning, tool calls, skill calls, one 15-step page at a time.
get_message_transcript(message_id)
Read it when the conversation refers to something an agent did — "it failed", "see what it found" — otherwise the thread alone will not explain the outcome.
Know who is talking
get_current_user tells you which account you are acting as, which is also
whose permissions apply. list_project_participants resolves the names behind
the ids in a project chat.
Then follow the references
Task keys (DEV-1234), @Task:<uuid> mention tokens, page links, and links to
other messages all appear as plain text in message content. Walking those is the
bridgeapp-context skill; use it rather than repeating its rules here.
Before you reply into BridgeApp
create_task_comment, send_channel_message, and send_direct_message post as
the signed-in user and are immediately visible to their colleagues. Summarize
back in this session first and let the user decide what gets posted, unless they
asked for exactly that 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.
- 2mo ago First seen · 57 lines · 61 tokens per session scan A eea7769b7090
bridgeapp-thread is a skill published in the GitHub repository MathAndMagic/bridgeapp-plugin (0 stars, last pushed 11d ago), licensed MIT. It adds 61 tokens to every session and 487 once invoked, about $0.0002 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 2026-08-31.
bridgeapp-thread compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| bridgeapp-threadMathAndMagic/bridgeapp-plugin | Skill | 0 | 11d ago | MIT | A | 61 | Claude Code |
| imagegenopenai/codex | Skill | 135k | today | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 100k | today | Apache-2.0 | A | 19 | Claude Code |
| browser-automationopenclaw/openclaw | Skill | 394k | today | MIT | A | 36 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 80k | 8d ago | MIT | A | 200 | Claude Code, Codex |
| next-cache-components-adoptionvercel/next.js | Skill | 144k | today | MIT | A | 95 | Claude Code |
| chat-pet-sprite-creationmicrosoft/vscode | Skill | 195k | today | MIT | A | 53 | Claude Code, Codex |