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 uk-agents/uk-legal-plugins --skill oscola-build-citationgit clone --depth 1 https://github.com/uk-agents/uk-legal-pluginsWrote 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/uk-agents/uk-legal-plugins/oscola-build-citation)<a href="https://agentmods.dev/skills/uk-agents/uk-legal-plugins/oscola-build-citation"><img src="https://agentmods.dev/badge/skills/uk-agents/uk-legal-plugins/oscola-build-citation/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/uk-agents/uk-legal-plugins/oscola-build-citation"><img src="https://agentmods.dev/badge/skills/uk-agents/uk-legal-plugins/oscola-build-citation.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 | $0.00100 | $0.01421 |
| Opus 5 | $0.00050 | $0.00711 |
| Sonnet 5 | $0.00020 | $0.00284 |
| Haiku 4.5 | $0.00010 | $0.00142 |
Grade A, and why
oscola-build-citation 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 9d 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 — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/oscola-build-citation
- Identify the source type: case / statute / SI / Hansard / journal article.
- Verify first:
citations_resolve(input=...)with the identifier the user gave. - If
not_found, stop — tell the user; do not format an unverified citation. - If resolved, build OSCOLA from the authoritative fields in the result.
- Tag
[uk-legal MCP — verified]; note any discrepancy with the user's input.
Purpose
Construct a correctly formatted OSCOLA citation for a UK legal source — after verifying that the source exists in the UK legal record. The failure mode this prevents: an agent formatting plausible-looking OSCOLA fields (correct year bracket style, court abbreviation, report reference) for a source that does not exist, or that differs in key details from what the user provided. Verification before formatting is the discipline.
Workflow
Source discipline: If a
uk-legal MCPtool returns empty or errored (status:empty/not_found/upstream_validation/ etc.), do NOT supplement from training data or web search. Report the empty result to the user with the tool'snext_steps/detailfield surfaced, and ask for clarifying information (different spelling of a name, a date range, the source URL) rather than fabricating a plausible-looking answer. Empty results are HONEST signal — not a failure mode to paper over.
Step 1 — Identify the source type
Determine which source type the user is asking to cite:
| Type | Examples |
|---|---|
| Case | R v Brown, Donoghue v Stevenson, a neutral citation |
| Statute | Housing Act 1988, Equality Act 2010, a section reference |
| SI | SI 2021/1234, a short title |
| Hansard | HL Deb vol N col M, a member's speech reference |
| Journal article | Author, title, journal, volume |
If the source type is ambiguous from the user's request, ask before proceeding.
Step 2 — Verify first
Call citations_resolve(input=...) with whatever identifier the user provided: a
neutral citation, statute short title, SI number, Hansard column reference, or URI.
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.
- 9d ago First seen · 135 lines · 100 tokens per session scan A e05d23954609
oscola-build-citation is a skill published in the GitHub repository uk-agents/uk-legal-plugins (9 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 100 tokens to every session and 1,421 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 2026-09-03.
Other skills, from other repositories
brand-safety-compliance
Scans outbound copy or creator-submitted content for 6 compliance red lines — medical/efficacy, exaggeration/absolute, beauty-permanence, financial/income, fake-scarcity, fake-rapport — and returns a block/warn verdict with fix suggestions. Use when the user asks to check, scan, review, or vet copy before sending, or…
ask
Answer a question from a finished study, citing back into its evidence, and say plainly when the study does not cover it.
compare
Set two term tables against each other — same concept different term, same term different concept, and what each covers that the other lacks.
enablement-course
Assemble an internal AI enablement course for a company's own employees, sized to where they actually are rather than where a vendor deck assumes they are. Produces the session plan, per-session content and exercises, a facilitator guide for a non-expert, and a way to tell whether it worked. Builds on the tech stack…
study-deps
Use when pulling upstream source or cloning a dependency at its installed version to study internals, read code, or create pinned worktrees.
brief
Use when confusion is only “huh,” “wait, what,” “sorry, you lost me,” or “slow down; explain simply and keep it short.”.