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 runxhq/runx --skill contract-draftgit clone --depth 1 https://github.com/runxhq/runxWrote 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/runxhq/runx/contract-draft)<a href="https://agentmods.dev/skills/runxhq/runx/contract-draft"><img src="https://agentmods.dev/badge/skills/runxhq/runx/contract-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/skills/runxhq/runx/contract-draft"><img src="https://agentmods.dev/badge/skills/runxhq/runx/contract-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 | $0.00037 | $0.00586 |
| Opus 5.5 | $0.00015 | $0.00234 |
| Sonnet 5.5 | $0.00007 | $0.00117 |
| Haiku 4.5 | $0.00004 | $0.00059 |
Grade A, and why
contract-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 2d 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 — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Contract Draft
Draft a contract without letting the drafting agent silently rewrite the template. The template, parties, and terms are the only evidence; the agent assembles clause text, and deterministic code re-renders every baseline with the supplied values and reconciles the draft against it. A clause may differ from its rendered baseline only through a declared deviation with a reason.
This is not legal advice and does not replace counsel. It is an execution boundary for template fidelity: the receipt proves which template version was drafted, which terms were bound, and which deviations were declared.
Procedure
- Admission requires a complete template (id, version, title, clauses with
baselines), explicit parties, and every
required_termskey present interms. Missing evidence stops before the drafting agent runs. - Native
data.digestbinds the exact template, parties, and terms. - The drafting agent assembles clause text and declares any deviations.
- Deterministic reconciliation re-renders each baseline with the supplied
values (
{{provider.legal_name}},{{terms.fee_usd}}, and similar paths). A clause must match its rendered baseline exactly, or carry a declared deviation with a reason. Undeclared deviations, deviations that match the baseline anyway, unknown clause targets, unresolved placeholders, and missing clauses all refuse. - A drafted verdict carries the document and a send proposal gated on a human
approver through
message-send.delivery_performedis always false.
Output
contract_draft (runx/contract-draft.draft.v1) carries decision, reason, the
document or null, confirmed deviations with baseline and text, the gated
send_proposal or null, validation, and the three input digests.
Inputs are template, parties, and terms.
Agent task contracts
contract-draft-assemble
Read template, parties, and terms from step inputs. Return draft_doc
with title, clauses (each id, heading, text), and deviations as an
array of clause_id plus reason entries. Render every placeholder from
the supplied values; never invent parties, amounts, or dates. Match each
baseline exactly unless a deviation is genuinely needed, and declare every
deviation with its reason. Do not add clauses the template does not define and
do not produce delivery instructions; delivery belongs to the gated proposal.
What ships with it
8 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.
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.
- 2d ago Changed dc417e9b562d
- 9d ago First seen · 53 lines · 37 tokens per session scan A 66a8c18c5bb8
contract-draft is a skill published in the GitHub repository runxhq/runx (104 stars, last pushed 2d ago), licensed Apache-2.0. It adds 37 tokens to every session and 586 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 2026-10-18.
Other skills, from other repositories
dd-risk-scoring
Calculate weighted risk scores from specialist agent reports. Use when synthesizing multiple due diligence reports into an overall investment risk assessment.
dd-synthesis
Synthesize findings from multiple specialist agents into a coherent investment recommendation. Use when combining reports from 9+ specialist agents into a single decision document.
dd-report-format
Standard output format for due diligence analysis reports. Use when producing your final analysis to ensure consistency across all specialist agents.
dd-sourcing
Document sources properly for due diligence reports. Use when citing any external data, ensuring full traceability and auditability of findings.
dd-verification
Verify claims in pitch decks and founder statements using multiple independent sources. Use when analyzing any claim about market size, traction, team background, or competitive positioning.
rule6-rights-gate
Hard Rule 6 pre-publication rights gate — check licensing/provenance AND likeness/voice consent over a generated or third-party media asset before publish/use, and emit the machine-readable gate record. Use at the S4 Verify step of content/image, content/video, content/audio-assets (or any asset headed for…