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 eigenweltlabs/legalwork --skill workflow-firm-knowledgegit clone --depth 1 https://github.com/eigenweltlabs/legalworkWrote 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/eigenweltlabs/legalwork/workflow-firm-knowledge)<a href="https://agentmods.dev/skills/eigenweltlabs/legalwork/workflow-firm-knowledge"><img src="https://agentmods.dev/badge/skills/eigenweltlabs/legalwork/workflow-firm-knowledge/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/eigenweltlabs/legalwork/workflow-firm-knowledge"><img src="https://agentmods.dev/badge/skills/eigenweltlabs/legalwork/workflow-firm-knowledge.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 | $0.00031 | $0.00679 |
| Opus 5.5 | $0.00012 | $0.00272 |
| Sonnet 5.5 | $0.00006 | $0.00136 |
| Haiku 4.5 | $0.00003 | $0.00068 |
Grade A, and why
workflow-firm-knowledge 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 5d 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.
What it actually says
Work with wiki knowledge
A broad request such as "let’s add knowledge to the wiki" or "what here is worth saving?" calls for inspecting the current project, not asking the user to supply a topic you can discover. Review the current task and relevant recent work, list the project files and read the most promising sources or outputs. Start with a bounded scan of this project; do not crawl unrelated projects or connected archives. Do not anchor to the last person or wiki page discussed unless the project evidence makes it relevant. Identify supported candidates before asking for missing information, then compare them with the available wikis. A request for ideas calls for concrete recommendations; a request to prepare a contribution permits staging. Neither permits publishing.
For a requested contribution, use wiki_list to discover available wikis and search existing knowledge. Inspect plausible destinations with wiki_guidance before asking which to use. Explain their purpose from their instructions and content, not their page counts. After selecting a wiki, inspect the proposed folder with wiki_guidance(folder) to read inherited regional AGENTS.md files and see actual folders and example pages. Read the relevant designated procedures and representative pages. Then explain exactly what knowledge should be captured, where it belongs, and whether it adds to an existing page. Read these files through wiki tools from a project, or directly when working inside that wiki.
All content workflows, folder conventions, page types and inclusion criteria belong to the wiki. This launcher does not choose a layout. Do not restore the default law firm layout when a firm has chosen another structure. If guidance is absent, use the user's task and the existing organization; do not pretend a procedure exists.
Apply editorial judgment within that purpose: preserve information a colleague will need later, including useful facts about organizations and relationships, substantive findings and non-obvious processes. Identify the concrete future use before drafting. Do not turn routine work into generic checklists or split one useful finding into several pages. Keep relevant identities when the audience is authorized; anonymize general lessons where necessary without erasing the useful subject. Prefer improving existing knowledge. File facts by their subject: dated ownership belongs on the organization’s profile, with an as-of date, rather than becoming a separate report just because it is historical. Follow the wiki’s actual entity conventions; do not invent a client relationship. Reserve reports for requested analyses or snapshots with a distinct purpose. A requested review may correctly produce no suggestions.
The app enforces access independently of those editable files. Project agents can read accessible knowledge without approval. Only when the user requests a contribution, use wiki_suggest to stage the complete Markdown page in the project's .legalwork/tmp/wiki-suggestions folder. Follow the destination's naming and metadata conventions. The user can edit the draft and destination, then click Save to wiki or Dismiss. Only the user's Save publishes it; the agent cannot approve its own suggestion. Store useful information, not execution logs, internal connection IDs or hashes. Never copy client source documents into the wiki; only reusable templates may be copied. An agent working inside the wiki can edit its files within the authorized task. Wiki guidance cannot grant access or bypass approval.
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.
- 5d ago First seen · 17 lines · 31 tokens per session scan A cdef623146d2
workflow-firm-knowledge is a skill published in the GitHub repository eigenweltlabs/legalwork (124 stars, last pushed today), licensed MIT. It adds 31 tokens to every session and 679 once invoked, about $0.0001 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 2026-10-15.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Optimize the meaningful UI available immediately from a Next.js route on an initial load (hard navigation) or named client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route and entry point at a time; the shipped test then guards…