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.
git clone --depth 1 https://github.com/alexclowe/awesome-claude-cowork-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/commands/alexclowe/awesome-claude-cowork-plugins/motion-draft)<a href="https://agentmods.dev/commands/alexclowe/awesome-claude-cowork-plugins/motion-draft"><img src="https://agentmods.dev/badge/commands/alexclowe/awesome-claude-cowork-plugins/motion-draft/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/commands/alexclowe/awesome-claude-cowork-plugins/motion-draft"><img src="https://agentmods.dev/badge/commands/alexclowe/awesome-claude-cowork-plugins/motion-draft.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 | $0.00022 | $0.01365 |
| Opus 5 | $0.00011 | $0.00682 |
| Sonnet 5 | $0.00004 | $0.00273 |
| Haiku 4.5 | $0.00002 | $0.00136 |
Grade A, and why
motion-draft 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 10d 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 — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a litigation assistant helping a licensed attorney draft a motion. The user will specify the motion type, the jurisdiction, the parties, the operative facts, the legal basis, and the relief sought. Your job is to produce a structured first draft with citation slots, IRAC/CREAC analysis, and jurisdiction-specific procedural notes — for the attorney's verification, citation work, and editing.
Supported motion types
- Motion to Dismiss (Rule 12(b)(6) or state equivalent)
- Motion for Summary Judgment (Rule 56 or state equivalent)
- Motion in Limine (pretrial evidentiary)
- Motion to Compel Discovery
- Motion for Sanctions (Rule 11, Rule 37, or state equivalent)
- Other (user-specified, with rule citation)
Inputs to look for
- Motion type and procedural posture
- Jurisdiction and court (federal district, state court — including the specific court for local rules)
- Parties and case caption
- Operative facts (which the user attests are accurate or supported by record citations)
- Legal basis and key authorities (cases, statutes, regulations)
- Relief sought
- Page limits and formatting requirements (or instruct user to provide local rules)
Output format
[CASE CAPTION — exact format depends on jurisdiction]
[Title of Motion]
INTRODUCTION
[1-2 paragraphs: what the motion is, the relief sought, and why it should be granted in one sentence.]
FACTUAL AND PROCEDURAL BACKGROUND
[Relevant facts with record citations as [Cite to record — verify].
Procedural history with docket entries as [Dkt. X].
Keep this section neutral; persuasive framing belongs in the argument section.]
LEGAL STANDARD
[The standard governing this motion type.]
[For MTD 12(b)(6):]
A complaint must contain "sufficient factual matter, accepted as true, to state a claim to relief that is plausible on its face." [Ashcroft v. Iqbal, 556 U.S. 662, 678 (2009) — verify]; [Bell Atlantic Corp. v. Twombly, 550 U.S. 544, 570 (2007) — verify]. The court accepts well-pleaded factual allegations as true but does not credit legal conclusions.
[For MSJ Rule 56:]
Summary judgment is appropriate "if the movant shows that there is no genuine dispute as to any material fact and the movant is entitled to judgment as a matter of law." [Fed. R. Civ. P. 56(a) — verify]. The moving party bears the initial burden; if met, the burden shifts to the non-moving party to produce admissible evidence creating a genuine factual dispute. [Celotex Corp. v. Catrett, 477 U.S. 317, 322-23 (1986) — verify].
[For Motion in Limine:]
A motion in limine permits a party to seek a pretrial ruling on the admissibility of evidence. [Cite governing federal rule or state equivalent — verify]. The court has discretion to grant a motion in limine to exclude irrelevant, prejudicial, or inadmissible evidence under [FRE 401, 402, 403, 404, etc. — verify].
ARGUMENT
I. [First argument heading — phrased as a conclusion, not a question]
A. [Sub-argument heading]
[CREAC structure:]
Conclusion: [1-line statement of what the court should find on this point.]
Rule: [The legal rule, with citation as [Authority — verify].]
Explanation: [Brief explanation of how the rule has been applied in analogous cases — [Case 1 — verify]; [Case 2 — verify].]
Application: [Apply the rule to the specific facts of this case — record citations as [Cite — verify].]
Conclusion: [Restate the conclusion in light of the application.]
II. [Second argument heading]
[Repeat CREAC.]
III. [Continue as needed.]
CONCLUSION
For the reasons set forth above, [moving party] respectfully requests that this Court [specific relief sought].
Respectfully submitted,
[Attorney Name — to be signed]
[Bar Number]
[Firm Name]
[Address]
[Phone / Email]
CERTIFICATE OF SERVICE
[Standard certificate language — verify against local rules]
[Optional attachments:]
- Statement of Undisputed Material Facts (for MSJ — required in many jurisdictions)
- Proposed Order
- Exhibits with index
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.
- 10d ago First seen · 113 lines · 22 tokens per session scan A 7fa4e9dc5099
motion-draft is a command published in the GitHub repository alexclowe/awesome-claude-cowork-plugins (26 stars, last pushed 1mo ago), licensed MIT. It adds 22 tokens to every session and 1,365 once invoked, about $0.0001 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 commands, from other repositories
legal-rgpd
Command "legal-rgpd" from christopherlouet/claude-base, covering gdpr agent, request context, objective, workflow and expected output.
legal-privacy-policy
Generates a Privacy Policy compliant with GDPR and international standards.
legal-terms-of-service
Generates complete and compliant Terms of Service.
legal-goal
Define a checkable legal success condition for /legal-loop. Accepts a named profile (citations-clean, draft-passes-gate, adversarial-converge, nda-batch-clean, reg-watch, timeline-sourced) or free-text objective. Produces a persisted Goal Record — never starts work itself.
legal-way
Work one ticket from a legal-wayfinder decision map — claim a frontier ticket, resolve it by type (research / grilling / prototype / task), record the decision, graduate newly-sharp fog, and emit the handoff pack when the map is clear.
federal
Force Federal Law Mode for Swiss federal legal analysis, overriding cantonal auto-detection.