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 purchase-approvalgit 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/purchase-approval)<a href="https://agentmods.dev/skills/runxhq/runx/purchase-approval"><img src="https://agentmods.dev/badge/skills/runxhq/runx/purchase-approval/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/purchase-approval"><img src="https://agentmods.dev/badge/skills/runxhq/runx/purchase-approval.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00035 | $0.00391 |
| Opus 5 | $0.00017 | $0.00196 |
| Sonnet 5 | $0.00007 | $0.00078 |
| Haiku 4.5 | $0.00003 | $0.00039 |
Grade A, and why
purchase-approval 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 5d 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.
What it actually says
Purchase Approval
Purchase Approval is the pre-spend decision gate. It answers one question, is
this purchase allowed under the supplied procurement policy, and it answers it
deterministically. It never moves money; spend and the payment rails own
execution, and this skill's sealed decision is what a caller carries into that
flow.
Procedure
- Native
data.digestbinds the exact purchase request and procurement policy before any judgment. - Deterministic rules apply in order: the vendor must be in
approved_vendors, the request currency must match the policy currency, and the amount must fit bothremaining_budgetandsingle_purchase_cap. The first failed rule refuses with a namedrefused_reason. - An in-policy amount that reaches
approval_thresholdreturnsneeds_humanwith the policy'shuman_lane(defaultprocurement-review); approval below the threshold isapproved. - A policy missing any required authority field refuses with
missing_policy_authorityand findings; nothing is inferred or invented.
spend_executed is always false. The decision packet carries both input
digests so a downstream spend can prove which request and policy were decided.
Output
purchase_approval (runx.purchase_approval.v1) carries decision
(approved, refused, needs_human), reason, vendor, amount,
currency, ceiling_amount, human_lane, refused_reason, policy_refs,
validation, and the two digests.
Inputs are purchase_request and procurement_policy.
What ships with it
2 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.
- 5d ago First seen · 39 lines · 35 tokens per session scan A 98364a1309bb
purchase-approval is a skill published in the GitHub repository runxhq/runx (84 stars, last pushed today), licensed Apache-2.0. It adds 35 tokens to every session and 391 once invoked, about $0.0002 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
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-risk-scoring
Calculate weighted risk scores from specialist agent reports. Use when synthesizing multiple due diligence reports into an overall investment risk assessment.
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.
compliance
This skill should be used when reviewing code handling PII, payment data, health records, audit logs, data retention, or IaC under GDPR, HIPAA, PCI DSS, SOC 2, ISO 27001, or SOX.