sign-receipt

sign-receipt is a skill for Claude Code, Codex from runxhq/runx. It costs 30 tokens per session (764 once invoked), scanned A, original, Apache-2.0.

A receipt-signing tool that records an attestation about an action performed outside Runx and links it to opaque evidence references. The signed receipt proves the record was sealed, not that the outside action actually happened.

In plain words
What is it for?
Use it to record manual console changes, externally approved decisions, or provider actions completed before a native integration exists.
Why use it?
It preserves the difference between an operator's claim and independent verification. This gives later workflows an auditable reference without pretending that a signature replaces provider or transaction evidence.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to record manual console changes, externally approved decisions, or provider actions completed before a native integration exists.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/runxhq/runx/sign-receipt
Install

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.

Any agent
npx skills add runxhq/runx --skill sign-receipt
Clone the repo
git clone --depth 1 https://github.com/runxhq/runx

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for sign-receipt

README.md
[![agentmods](https://agentmods.dev/badge/skills/runxhq/runx/sign-receipt/github.svg)](https://agentmods.dev/skills/runxhq/runx/sign-receipt)
Your own site
<a href="https://agentmods.dev/skills/runxhq/runx/sign-receipt"><img src="https://agentmods.dev/badge/skills/runxhq/runx/sign-receipt/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.

agentmods 80×15 button for sign-receipt

Your own site · 80×15
<a href="https://agentmods.dev/skills/runxhq/runx/sign-receipt"><img src="https://agentmods.dev/badge/skills/runxhq/runx/sign-receipt.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 30 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 764 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00030 $0.00764
Opus 5 $0.00015 $0.00382
Sonnet 5 $0.00006 $0.00153
Haiku 4.5 $0.00003 $0.00076

Measured 5d ago against content hash 512935aa95e2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

sign-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 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.

skills/sign-receipt/SKILL.md · 80 lines

How it starts

The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Sign Receipt

Record a bounded attestation about something that happened outside Runx so a later governed run can cite exactly what was claimed, by whom, on which evidence, and for what reliance scope. The native Runx receipt signature proves the attestation packet was sealed without later modification. It does not prove the external action itself happened.

That distinction makes this skill useful without turning a signature into a fictional provider verifier. The actual proof remains in the referenced commit, provider object, approval record, transaction, or other evidence system.

When to use it

Use sign-receipt when an operator performed a legitimate off-runtime action and downstream automation needs a stable, auditable assertion about it. Examples include a manual console change, an externally approved decision, or a provider operation completed before a native adapter existed.

Do not use it to launder an unsupported claim, copy raw evidence into a receipt, or replace a provider readback surface that Runx can actually call. If the external record is available through a governed reader, prefer that stronger evidence path.

How it works

  1. Supply the action, named principal, exact claim, optional reliance scope, and bounded opaque evidence references.
  2. Each evidence item names only a stable ref, SHA-256 digest, and what that evidence is asserted to prove. Raw messages, receipts, secrets, and personal records are not accepted.
  3. Native receipt.attest validates completeness, rejects duplicates and secret-shaped material, and computes a deterministic attestation digest.
  4. The normal Runx receipt signer seals that packet into the parent run.
  5. Later consumers can verify the receipt and decide whether its declared reliance scope is sufficient for their own action.

The skill never calls the provider named in the claim and never appends to an external ledger. Its signature mode and proof boundary are explicit in the result.

Inputs and result

Read the full file on GitHub · 80 lines

Files

What ships with it

5 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.

Changes

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.

  1. 5d ago First seen · 80 lines · 30 tokens per session scan A 512935aa95e2

Subscribe to this mod's changes

sign-receipt is a skill published in the GitHub repository runxhq/runx (84 stars, last pushed today), licensed Apache-2.0. It adds 30 tokens to every session and 764 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.