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 audit-receiptgit 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/audit-receipt)<a href="https://agentmods.dev/skills/runxhq/runx/audit-receipt"><img src="https://agentmods.dev/badge/skills/runxhq/runx/audit-receipt.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 150 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00047 | $0.01843 |
| Opus 5 | $0.00023 | $0.00922 |
| Sonnet 5 | $0.00009 | $0.00369 |
| Haiku 4.5 | $0.00005 | $0.00184 |
Grade A, and why
audit-receipt 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 8d 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 — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Receipt Auditor
Audit a sealed run for authority over-reach, binding the review to its native receipt identity and verification posture.
Runx seals a receipt for every run. This skill resolves the exact receipt id
through ledger read, which returns the Rust-owned redacted detail projection
for signed authority, acts, decisions, artifacts, lineage, and verification. It answers one governance
question: did the run stay inside the authority it was granted? It flags scopes
exercised that were never granted, acts that claim an approval requirement or
decision without matching host-attested evidence, refusals that were not
recorded, and any raw secret material that leaked into the receipt. It pairs
with least-privilege: that one narrows a
grant from usage, this one verifies a run honored its grant.
Composes
ledger#read
What this skill does
- Read the proof and the acts. From the receipt, extract the granted authority (the proof) and the scopes the acts actually exercised.
- Diff exercised against granted. Any exercised scope not covered by the proof is over-reach.
- Check declared approval. When an act's authority or effect evidence says exact approval was required, the receipt must carry the matching host-attested decision. A routine write inside its admitted grant does not acquire an approval requirement merely because it changed provider state.
- Check exposure. The receipt must carry only hashed material references; a raw secret in the receipt is a leak.
- Verdict.
clean,anomaly, orneeds_more_evidence, with the exact findings and a recommendation for each anomaly.
Core principles
- The receipt is the evidence. Audit what the receipt records, not what the skill claims it did.
- Granted is the ceiling. Exercised authority must be a subset of the proof; anything beyond is over-reach, full stop.
- Approval follows the act contract. Missing or mismatched approval is an anomaly only when the signed authority/effect evidence required that exact decision. Never infer human-approval policy from a write-shaped verb.
- No raw material. A receipt must reference material by hash; raw credential material in a receipt is a leak, not a convenience.
- Absence of evidence is not clean. With no receipt or an unattributable
one, return
needs_more_evidence, neverclean.
What ships with it
4 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.
- 8d ago First seen · 179 lines · 47 tokens per session scan A 0a2576b0df69
audit-receipt is a skill published in the GitHub repository runxhq/runx (84 stars, last pushed yesterday), licensed Apache-2.0. It adds 47 tokens to every session and 1,843 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 2026-08-30.
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.
codew-release-qa-sweep
Use before claiming Codewhale release work is done: run the full gate sweep and list the manual QA targets.