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 LegalQuants/lq-skills --skill redfern-schedulegit clone --depth 1 https://github.com/LegalQuants/lq-skillsWrote 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/legalquants/lq-skills/redfern-schedule)<a href="https://agentmods.dev/skills/legalquants/lq-skills/redfern-schedule"><img src="https://agentmods.dev/badge/skills/legalquants/lq-skills/redfern-schedule/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/legalquants/lq-skills/redfern-schedule"><img src="https://agentmods.dev/badge/skills/legalquants/lq-skills/redfern-schedule.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 | $0.00187 | $0.03723 |
| Opus 5 | $0.00093 | $0.01861 |
| Sonnet 5 | $0.00037 | $0.00745 |
| Haiku 4.5 | $0.00019 | $0.00372 |
Grade A, and why
redfern-schedule 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 12d 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 — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.
YOU ARE ABOUT TO DO HIGHLY PRIVILEGED WORK. PLEASE CHECK THE RULES OF YOUR JURISDICTION, AS YOU MAY NEED TO SWITCH TO A LOCAL MODEL. BEFORE YOU PROCEED, CONFIRM THAT YOU ARE FINE WITH PROCEEDING.
A Redfern Schedule carries the live substance of a dispute and is usually privileged and confidential. Assume local or on-premises execution. Do not send live schedule content to a cloud endpoint without the seat's rules, the parties' agreement, and the client's consent, and a check against the CIArb Guideline on the Use of AI in Arbitration (2025) and the applicable bar and ethics rules. This warning is enforced as the first step of the workflow below.
Redfern Schedule
Build and maintain the Redfern Schedule that organises requests to produce documents in international arbitration. The skill serves three roles from one artefact: the requesting party (who drafts the requests and the relevance-and-materiality case), the producing party (who states objections), and the tribunal (who rules). It applies the IBA Rules on the Taking of Evidence (2020) admissibility form and grounds for objection, holds version discipline across rounds, and tells the user where their own requests are weak. It enforces form. The legal calls stay with counsel.
Audience and design
- Audience. Arbitration counsel and the lawyers supervising them, acting in one of three roles (requesting party, producing party, tribunal). It assumes legal training and hands every substantive judgment back to the lawyer.
- Work shape. Bounded and transactional. The scope is constrained, the tests are explicit, and the skill surfaces deviations and frames the decision rather than choosing for the user. Speed matters, but never at the cost of an escalation trigger.
- How it handles confidence. A request that clearly passes or clearly fails the Article 3.3 gates is recorded as such with the reason. A borderline request is not silently resolved. It is named in the internal flags memo with the gate it strains, and the user decides whether to fix, narrow, or drop it. The skill surfaces uncertainty, it does not perform certainty.
What ships with it
14 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.
- evals/evals.json 5.7 KB
- evals/RESULTS.md 2.3 KB
- examples/example_producing.md 7.3 KB
- examples/example_requesting.md 4.9 KB
- examples/example_tribunal.md 7.8 KB
- examples/gold-fact-pattern.md 8.3 KB
- README.md 5.8 KB
- reference/CITATIONS.md 11 KB
- reference/iba-3-3-checklist.md 6.9 KB
- reference/iba-9-2-objections.md 9.6 KB
- reference/intake.md 2.8 KB
- reference/issue-matching.md 2.4 KB
- reference/regimes.md 5.5 KB
- reference/schedule-format.md 4.7 KB
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.
- 12d ago First seen · 150 lines · 187 tokens per session scan A 458ce898b276
redfern-schedule is a skill published in the GitHub repository LegalQuants/lq-skills (54 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 187 tokens to every session and 3,723 once invoked, about $0.0009 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 2026-08-30.
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
Format and structurally validate 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…
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.
iflytek-contract-intelligence-review
A contract-review workflow for scanned or digital agreements. It can recognize document text, examine clauses, detect risks, check compliance, and create translation summaries; its output is for review and is not formal legal advice.
legal-writer
Legal document drafting -- contracts, memos, briefs, complaints, demand letters, opinions, discovery, settlements, ToS, privacy policies. Full pipeline: document structure, per-section writing, Bluebook citation, case law lookup (CourtListener API), regulation lookup (eCFR API), DOCX output, and TDD-style verification…