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-task-creationgit 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-task-creation)<a href="https://agentmods.dev/skills/mathandmagic/bridgeapp-plugin/bridgeapp-task-creation"><img src="https://agentmods.dev/badge/skills/mathandmagic/bridgeapp-plugin/bridgeapp-task-creation/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-task-creation"><img src="https://agentmods.dev/badge/skills/mathandmagic/bridgeapp-plugin/bridgeapp-task-creation.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 | $0.00058 | $0.00626 |
| Opus 5.5 | $0.00023 | $0.00250 |
| Sonnet 5.5 | $0.00012 | $0.00125 |
| Haiku 4.5 | $0.00006 | $0.00063 |
Grade A, and why
bridgeapp-task-creation 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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Creating a BridgeApp task
You place the task. You do not solve it.
Before creating
Look for an existing task first. tasks_search on the feature and on the
error text. If something might already cover it, show the user what you found
and ask whether they still want a new one. A duplicate costs more than the
question.
Determine the project. From the chat the request came from, from the task being discussed, from what the user said. If it is genuinely unclear, ask — this is the one thing that should stop you. Everything else you can fill in or leave empty.
Then read the surrounding context before writing: the message and its thread,
whatever it references. get_task_create_context returns what a project accepts
— statuses, types, components, versions, assignable agents — so you can fill
fields instead of guessing at them.
Writing it
The description is a spec the assignee acts on, grounded only in what was actually discussed. Do not invent acceptance criteria nobody agreed to.
Carry over what makes it actionable: the originating thread, related tasks, the
error text as it appeared, the reproduction if there was one. Link them —
format_bridgeapp_mention when the text lives inside BridgeApp,
build_bridgeapp_link when it does not.
Set the type from the request. Use the type the user named; otherwise infer it from the nature of the work.
Create with what you have. A missing detail never blocks creation — only an unclear project, or a task that already exists.
What to reply
You are outside BridgeApp, so a mention token renders as raw text here. Give the user the task key, its title, and a URL they can open:
DEV-1234 — Fix the token exchange returning null
https://<workspace-host>/#/projects/<projectId>/board/<taskId>
Get the URL from build_bridgeapp_link with the task id from the create result.
Never write it by hand: the server knows the workspace host, which may be a
self-hosted domain of its own, and the route, which needs the project as well
as the task — there is no by-key URL.
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 Changed · -1 lines 5df8cdd0d0cb
- 2mo ago Changed · +2 lines 26da536f351b
- 2mo ago First seen · 66 lines · 58 tokens per session scan A 44315c145f1a
bridgeapp-task-creation is a skill published in the GitHub repository MathAndMagic/bridgeapp-plugin (0 stars, last pushed 11d ago), licensed MIT. It adds 58 tokens to every session and 626 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-task-creation compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| bridgeapp-task-creationMathAndMagic/bridgeapp-plugin | Skill | 0 | 11d ago | MIT | A | 58 | 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 |