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-taskgit 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)<a href="https://agentmods.dev/skills/mathandmagic/bridgeapp-plugin/bridgeapp-task"><img src="https://agentmods.dev/badge/skills/mathandmagic/bridgeapp-plugin/bridgeapp-task/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"><img src="https://agentmods.dev/badge/skills/mathandmagic/bridgeapp-plugin/bridgeapp-task.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 | $0.00070 | $0.00767 |
| Opus 5.5 | $0.00028 | $0.00307 |
| Sonnet 5.5 | $0.00014 | $0.00153 |
| Haiku 4.5 | $0.00007 | $0.00077 |
Grade A, and why
bridgeapp-task 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.
How it starts
The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Working from a BridgeApp task
A task alone is rarely enough to act on. It sits in a project that carries the conventions, and it points at conversations that carry the reasoning.
1. The task itself
get_task_by_key("DEV-1234") when you have the key
get_task(id) when you have the id
Then its graph, as the question requires:
| Tool | What it adds |
|---|---|
get_task_plan_context |
root-to-current chain with plan documents — start here for anything non-trivial |
list_task_comments |
the discussion, where scope usually changed |
list_task_subtasks |
how the work was broken down |
list_task_blockers |
what stops it |
list_task_blocked_tasks |
what it stops — matters before you touch anything |
list_task_pages |
attached documents |
Each pages at 15. Keep going until a page comes back short.
2. The project, which is where the rules live
Read these before you write code for a task:
get_project(id) name, description
get_project_brief(id) conventions, flow, links
get_company_brief() workspace-wide rules
The briefs are how you learn which repository this work belongs to. MCP exposes no structured repository, VCS, or integration field — the project's repository, its branch and PR conventions, its deploy flow, and any agent workflow are prose in the brief, if they are recorded at all.
So: read both briefs, and take what they say about repositories and process as the instruction. If neither names a repository and the task does not either, ask the user which one to work in rather than inferring it from the directory you happen to be sitting in.
Where a project has structure worth knowing — list_project_components,
list_project_milestones, list_project_versions,
list_project_participants, list_project_agents — pull it only when the task
turns on it: choosing a component for a new task, checking who owns an area,
seeing which agents can be assigned.
3. The conversations it points at
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 · 79 lines · 70 tokens per session scan A 9f6a75734e64
bridgeapp-task is a skill published in the GitHub repository MathAndMagic/bridgeapp-plugin (0 stars, last pushed 11d ago), licensed MIT. It adds 70 tokens to every session and 767 once invoked, about $0.0003 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 compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| bridgeapp-taskMathAndMagic/bridgeapp-plugin | Skill | 0 | 11d ago | MIT | A | 70 | 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 |