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 agentmods add skills/bks-lab/open-bridge/doc-systemnpx skills add bks-lab/open-bridge --skill doc-systemgit clone --depth 1 https://github.com/bks-lab/open-bridgeWrote 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/bks-lab/open-bridge/doc-system)<a href="https://agentmods.dev/skills/bks-lab/open-bridge/doc-system"><img src="https://agentmods.dev/badge/skills/bks-lab/open-bridge/doc-system.svg" alt="Measured on agentmods" 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 | $0.00103 | $0.00655 |
| Opus 5 | $0.00051 | $0.00328 |
| Sonnet 5 | $0.00021 | $0.00131 |
| Haiku 4.5 | $0.00010 | $0.00065 |
Grade A, and why
doc-system 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 4d 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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Doc-System
Document intake, processing, and monitoring. Read the referenced file ONLY when triggered.
Guard — run BEFORE anything else
- Read
bridge-config.yaml. Ifdoc_sensor.enabledis nottrueor the block is missing → inform user "doc-system is not enabled in bridge-config.yaml. Setdoc_sensor.enabled: trueanddoc_sensor.onedrive_root(the documents root — name is historical, any local folder works)" and stop. - Resolve
${onedrive_root}fromdoc_sensor.onedrive_root(expand~and$HOME). If the path is empty or the directory does not exist → inform "documents root{value}not reachable" and stop. Do not proceed with a blank interpolation.
REQUIRED: Load routing sources
Before EVERY processing run (after the guard above):
Read("workflow/contexts/doc-system.yaml")
# Personas referenced in context.personas → load automatically.
# Example: if context.personas contains
# freelancer: my-freelancer
# private: my-private
# then:
Read("identity/personas/my-freelancer.yaml")
Read("identity/personas/my-private.yaml")
workflow/contexts/doc-system.yaml is the single source of truth for
areas, naming, tags, routing rules, and anti-patterns. Personas supply
concrete target paths via destinations:.
NEVER routing rules from memory — ALWAYS from context.yaml!
For edge cases, additionally read the local _INFO.md of the affected area
(${onedrive_root}/<areas-root>/<area>/_INFO.md — path convention
from context.areas[*].path) — as a detail hint for human maintenance, not
as an override for context.yaml.
Decision Tree
User wants to...
├── Scan inbox / show what's new → Read references/inbox.md
├── Process documents → Read references/process.md
├── Check document queue status → Read references/status.md
└── Questions about doc system → Answer from this file
Path resolution
- Read
bridge-config.yaml→doc_sensor.onedrive_root - Expand
~to$HOME - Areas root comes from
context.areas[*].path(e.g.2_AREAS/for PARA,20_<area>/for Johnny Decimal, or anything for custom setup)
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 4d ago First seen · 74 lines · 103 tokens per session scan A acce22361f2d
doc-system is a skill published in the GitHub repository bks-lab/open-bridge (8 stars, last pushed 4d ago), licensed MIT. It adds 103 tokens to every session and 655 once invoked, about $0.0005 per session on Opus 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.
Other skills, from other repositories
dsh-translate-docs
Manually run the extended DeepSeek Harness bilingual-document workflow, including generated briefings, delegated prose translation, whole-document translation, and scoped pairing verification.
xlsx
Comprehensive spreadsheet creation, editing, and analysis with support for formulas, formatting, data analysis, and visualization. When Claude needs to work with spreadsheets (.xlsx, .xlsm, .csv, .tsv, etc) for: (1) Creating new spreadsheets with formulas and formatting, (2) Reading or analyzing data, (3) Modify…
Comprehensive PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms. When Claude needs to fill in a PDF form or programmatically process, generate, or analyze PDF documents at scale.
Use when the user asks to process PDF documents.
xlsx
Use when the user asks to create, edit, or analyze spreadsheets.
pptx
Presentation creation, editing, and analysis. When Claude needs to work with presentations (.pptx files) for: (1) Creating new presentations, (2) Modifying or editing content, (3) Working with layouts, (4) Adding comments or speaker notes, or any other presentation tasks.