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 Stahl-G/briefloop --skill briefloop-externalgit clone --depth 1 https://github.com/Stahl-G/briefloopWrote 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/stahl-g/briefloop/briefloop-external)<a href="https://agentmods.dev/skills/stahl-g/briefloop/briefloop-external"><img src="https://agentmods.dev/badge/skills/stahl-g/briefloop/briefloop-external/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/stahl-g/briefloop/briefloop-external"><img src="https://agentmods.dev/badge/skills/stahl-g/briefloop/briefloop-external.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 | $0.00042 | $0.01074 |
| Opus 5.5 | $0.00017 | $0.00430 |
| Sonnet 5.5 | $0.00008 | $0.00215 |
| Haiku 4.5 | $0.00004 | $0.00107 |
Grade A, and why
briefloop-external 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 14d 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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
BriefLoop 外部报告入口
适用于用户明确选择的本地 BriefLoop 工作区。通过已运行的 BriefLoop 完成研究和报告生产;保留其模型、企业背景选择、模板与独立审阅要求。
连接与提交
支持 stdio MCP 的宿主可使用 briefloop mcp --workspace "/absolute/workspace"(随下一版发布)。先调用 briefloop_discover 确认 ready=true;其余工具为 briefloop_inspect/source/submit/query/read/revise/export/download,字段与下表和 CLI 下载参数一致,不传 action、工作区、URL 或 Token。briefloop_download 使用 job_id 和明确本机文件路径 output。连接固定启动时选定的绝对路径及工作区身份,不创建或启动后台。停止 MCP 连接不取消已接收任务,重连后查询原任务并用原 request_id、原内容重试未知写结果。
使用已安装的 briefloop,或同一 Python 环境中的 python -m briefloop。先执行:
briefloop external --workspace "/absolute/workspace" discover
该命令不会创建目录、数据库或启动服务。ready=false 时将实际原因告诉用户;需要先在 BriefLoop 打开该工作区。不要改连其他工作区。无需读取、复制或展示 API Key。
将请求保存为 UTF-8 JSON 文件,然后执行:
briefloop external --workspace "/absolute/workspace" request --file request.json
可用请求:
| action | 字段 | 返回内容 |
|---|---|---|
| inspect | 无 | 最近来源与稿件 ID;列表有数量上限 |
| source | source_id | 保存的来源正文与出处 |
| submit | request_id、requirements、source_ids | job_id、run_id |
| query | job_id | 状态、错误、对应版本和文件是否可用 |
| read | version_id | 保存的 Markdown 与 editor_document |
| revise | request_id、base_version、editor_document | 新 version_id |
| export | request_id、version_id | Word 导出 job_id |
先 inspect / source 确认所选材料,再提交用户要求。例如:
{"action":"submit","request_id":"report-unique-id","source_ids":["src_actual_id"],"requirements":{"title":"本期简报","objective":"概括已上传材料的变化及影响","allow_web":false,"writing_mode":"general","target_words":500,"max_words":700}}
ID 必须来自实际响应。企业内报告使用 writing_mode: "internal_report";若系统要求先选择企业背景维护方式,应在 BriefLoop 完成选择,不能改成 general 绕过。requirements 使用 BriefLoop 既有需求字段;模型沿用工作区设置,接口不暗改配置。
重试与进度
每次新的写操作生成一个唯一 request_id,保存完整请求和返回 ID。响应丢失时,用原 ID、原内容重试;replayed=true 表示返回既有结果。同一 ID 改内容会报冲突。不要靠换 ID 恢复未知结果,否则会新建任务。
提交后向用户报告任务已接收,并用 query 查询原 job;无需一次调用等完整报告。查询间隔适当退避,例如 5 秒到 30 秒。失败、取消、中断是明确状态,报告实际错误及已保存稿件,不自动重建任务。latest_version_id 是该报告的最新稿件,可能来自后续修订;导出必须明确选定版本。
改稿与 Word
先 read 精确版本,保留完整 editor_document 的图、表、引用和格式,仅修改用户要求的部分;用该版本作 base_version。发生“已有更新”冲突时重新读取并合并,不能覆盖新稿或丢掉未修改节点。保存成功后再次读取新版本。
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.
- 14d ago Changed · +2 lines 105dfbeb1396
- 1mo ago First seen · 63 lines · 42 tokens per session scan A 7d85df749991
briefloop-external is a skill published in the GitHub repository Stahl-G/briefloop (9 stars, last pushed yesterday), licensed MIT. It adds 42 tokens to every session and 1,074 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 2026-09-14.
Other skills, from other repositories
accounting-software-selection
Scores shortlisted accounting packages against 57 evidence-backed fields, emitted as CSV, SQL, JSON Schema or Notion on request. Use for choosing accounting software.
accounting-audit-system-builder
Routes an accounting or audit request to the right module skill, from software selection through monthly closing, asking only what is missing. Use for books of accounts or audit files.
geo-proposal
Auto-generate a professional, client-ready GEO service proposal from audit data. Creates a full proposal in markdown and PDF including executive summary, findings, recommended service packages (Basic/Standard/Premium), pricing, timeline, and terms. Use when user says "proposal", "proposta", "offerta", "preventivo"…
mira-annotation-review
Review MIRA annotations in Markdown documents for semantic correctness, Markdown dialect validity, preservation, and relation integrity. Use for md, smd, qmd, and myst files containing research objects such as claims, evidence, questions, protocols, requests, typed claims, ids, and relations. Produces actionable…
document-generation
Generate Word (.docx), Excel (.xlsx) and PowerPoint (.pptx) documents and fill existing PDF forms, from real NetClaw data, with per-element provenance and no fabrication. This is the generic document-writing engine (tool surface, tagged-value shapes, fabrication rules). For the four standard NetClaw report…
network-report-documents
The four standard NetClaw document compositions — a change-record Word document from a real ServiceNow CR plus device state, an interface/config audit workbook from real device queries, an executive summary deck with an embedded topology diagram, and a required PDF form filled from real data. Use when an operator asks…