Borrowing it
Nothing to install: this file belongs to zeweihan/aiworkdeck. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/zeweihan/aiworkdeck/master/.claude/agents/eng-infra.mdgit clone --depth 1 https://github.com/zeweihan/aiworkdeckWrote 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/agents/zeweihan/aiworkdeck/eng-infra)<a href="https://agentmods.dev/agents/zeweihan/aiworkdeck/eng-infra"><img src="https://agentmods.dev/badge/agents/zeweihan/aiworkdeck/eng-infra/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/agents/zeweihan/aiworkdeck/eng-infra"><img src="https://agentmods.dev/badge/agents/zeweihan/aiworkdeck/eng-infra.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 | $0.00066 | $0.25809 |
| Opus 5.5 | $0.00026 | $0.10324 |
| Sonnet 5.5 | $0.00013 | $0.05162 |
| Haiku 4.5 | $0.00007 | $0.02581 |
Grade A, and why
eng-infra scanned grade A with 2 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
已在 0.31.0 纠正。**核对法:两站 `curl -L .../AI-WorkDeck-Office-Addin.exe` 的字节数应当不同** Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
- **Electron 主进程禁用 `spawnSync`/任何同步阻塞调用**:v0.21.0 新机首启 10-30 秒无窗口、 The source is not reproduced here
Licensed AGPL-3.0
The repository is licensed AGPL-3.0, which this catalogue does not treat as permission to reproduce the file. Read it at the source.
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 4249deba51b1
- 1mo ago Changed f3261b2809b3
- 1mo ago Changed · +7 lines cb8c13e7f4d5
- 1mo ago Changed f9a1eef08070
- 1mo ago Changed · +12 lines 30a461a65d1e
- 1mo ago Changed · +1 lines af8b271a83ab
- 1mo ago Changed · +13 lines 92430423a0ce
- 1mo ago Changed · +2 lines 9eea5829ba04
- 1mo ago Changed · +15 lines 7bfea7baf8e4
- 1mo ago First seen · 484 lines · 66 tokens per session scan A 42f641581430
eng-infra is an agent published in the GitHub repository zeweihan/aiworkdeck (151 stars, last pushed 28d ago), licensed AGPL-3.0. It adds 66 tokens to every session and 25,809 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 2 findings (makes network calls, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
eng-infra compared with agents from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| eng-infrazeweihan/aiworkdeck | Agent | 151 | 28d ago | AGPL-3.0 | A | 66 | Claude Code |
| git-summaryopensolon/solon-ai | Agent | 470 | 3d ago | Apache-2.0 | A | 23 | Claude Code |
| ingest-refs-extractorchrisgagne/grounded-forge | Agent | 8 | yesterday | MIT | A | 83 | Claude Code |
| i18nzhimaAi/chatwiki | Agent | 2.1k | 21d ago | none | A | 7 | Claude Code |
| rag-evaluatorLucasSantana-Dev/sharekit | Agent | 2 | 4d ago | MIT | A | 68 | Claude Code |
| arbitration-orchestratorishwarjha/legalant | Agent | 6 | 6mo ago | MIT | A | 56 | Claude Code |
| ai-engineerT4LEL/Claude-Arsenal | Agent | 1 | 3mo ago | MIT | A | 50 | Claude Code |