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 start-tabular-reviewgit 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/start-tabular-review)<a href="https://agentmods.dev/skills/eigenweltlabs/legalwork/start-tabular-review"><img src="https://agentmods.dev/badge/skills/eigenweltlabs/legalwork/start-tabular-review/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/start-tabular-review"><img src="https://agentmods.dev/badge/skills/eigenweltlabs/legalwork/start-tabular-review.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 | $0.00043 | $0.01009 |
| Opus 5.5 | $0.00017 | $0.00404 |
| Sonnet 5.5 | $0.00009 | $0.00202 |
| Haiku 4.5 | $0.00004 | $0.00101 |
Grade A, and why
start-tabular-review 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 17d 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 — 33 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Start a tabular review
Use the native saved-review tools. The review runs independently of chat; its card shows progress and opens the table.
- Read
legalwork_review_settingsbefore selecting columns. Use the user's mandatory mode and models; never change settings or pass model overrides. - Use the exact project-relative paths already attached or named by the user. If paths are missing, browse with
legalwork_review_files, including itsnextCursorand folders. This is silent source discovery. Do not show a project inventory or calllegalwork_project_listjust to start a review. - Find suitable prompts with
legalwork_review_library. Search a short topic such ascommercialorNDA; if a phrase has no matches, try its main topic before inventing a replacement set. Reuse the returned definitions and fallback options. Preserve the requested scope; add bespoke columns only when needed. - Call
legalwork_review_createwith a name, files and columns. IDs and retry protection are handled automatically; do not generate UUIDs or run a shell command. Use the returned review id and revision inlegalwork_review_start. - For a start-only request, once all requested reviews have started, stop tool work. Reply with at most one short sentence in the user's language, such as “Review started.” / “Prüfung gestartet.” The live card supplies the details. Do not describe its position as above or below: its placement can change. Do not list columns, settings, counts, internal paths, or technical steps unless asked; do not poll or narrate setup between calls. Report an actual blocker briefly instead of claiming success.
Complete workflows and multiple reviews
When the user requests results or a downstream deliverable such as a DD report, start every requested review and retain their IDs. Use legalwork_review_wait with reviewIds and a bounded waitSeconds to wait for all of them together. Repeat while reviews are running; inspect every returned status and missing-review error. Read complete result coverage for each review with legalwork_review_results before synthesising the deliverable. Do not end the workflow merely because the first review started. One review may contain the full document class; internal workers batch execution without a document-count cap. Do not change the user’s mode or omit incompatible columns.
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.
- 17d ago Changed · +4 lines 84a2971f3d7b
- 18d ago First seen · 29 lines · 43 tokens per session scan A 07dbae18e566
start-tabular-review is a skill published in the GitHub repository eigenweltlabs/legalwork (123 stars, last pushed today), licensed MIT. It adds 43 tokens to every session and 1,009 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 2026-09-30.
Other skills, from other repositories
html-ppt-zhangzara-stencil-tablet
A workplace-safety compliance review for a manufacturing regulator — findings, the evidence chain, and the corrective mandate. Built as a decision-grade policy briefing deck for regulator, plant leadership.
treatment-plans
Formats and structurally validates local treatment-plan documentation after clinical decisions have already been supplied and verified by authorized licensed professionals. Use for source traceability, clinician-authored intervention records, goals and checkpoints, shared-decision records, reconciliation handoffs, and…
legal-hold
Issue, refresh, release, or report on legal holds — drafts the hold notice as .docx, updates legalhold fields in log.yaml, and calendars the next refresh. Use when the user says "issue a hold", "refresh hold", "release hold", or asks for a portfolio-wide hold status report.
handbook-updates
Diff a proposed handbook change against the current version, flag ripple effects and state supplement impacts. Use when user says "update the handbook", "add this to the handbook", "handbook change", or has a policy ready for insertion.
software-copyright-materials
A workflow for creating Chinese application materials for software copyright registration from a real software project.
employment-contract-templates
Create employment contracts, offer letters, and HR policy documents following legal best practices. Use when drafting employment agreements, creating HR policies, or standardizing employment documentation.