document-signing

document-signing is a skill for Claude Code, Codex from asgeirtj/system_prompts_leaks. It costs 28 tokens per session (1,257 once invoked), scanned A, original, CC0-1.0.

A document-signing helper that reviews files, prepares signing packets, and handles an authorized signing step. It checks signer details, required fields, dates, and attachments before anything is uploaded or sent.

In plain words
What is it for?
Use it to inspect a document, make a private checklist of fields and recipients, compare versions, or prepare an approved packet for signing.
Why use it?
It helps prevent sending the wrong document, missing required information, or involving the wrong recipient. It also keeps review separate from actions that need explicit approval.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: positional $N argument.

Good fit Use it to inspect a document, make a private checklist of fields and recipients, compare versions, or prepare an approved packet for signing.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/asgeirtj/system_prompts_leaks/document-signing
About the project

System Prompts Leaks is a collection of captured system instructions used to guide AI chatbots and coding agents before they receive user messages. It serves researchers and developers studying how different AI assistants are directed.

asgeirtj/system_prompts_leaks · 69,821 stars · on GitHub

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 asgeirtj/system_prompts_leaks --skill document-signing
Clone the repo
git clone --depth 1 https://github.com/asgeirtj/system_prompts_leaks

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 document-signing

README.md
[![agentmods](https://agentmods.dev/badge/skills/asgeirtj/system_prompts_leaks/document-signing/github.svg)](https://agentmods.dev/skills/asgeirtj/system_prompts_leaks/document-signing)
Your own site
<a href="https://agentmods.dev/skills/asgeirtj/system_prompts_leaks/document-signing"><img src="https://agentmods.dev/badge/skills/asgeirtj/system_prompts_leaks/document-signing/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 document-signing

Your own site · 80×15
<a href="https://agentmods.dev/skills/asgeirtj/system_prompts_leaks/document-signing"><img src="https://agentmods.dev/badge/skills/asgeirtj/system_prompts_leaks/document-signing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 28 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,257 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.
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 $0.00028 $0.01257
Opus 5.5 $0.00011 $0.00503
Sonnet 5.5 $0.00006 $0.00251
Haiku 4.5 $0.00003 $0.00126

Measured 12d ago against content hash 0a3e44adc7d7, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

document-signing 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 12d 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.

OpenAI/dots/skills/document-signing/SKILL.md · 75 lines

How it starts

The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Document signing

Review a document, prepare a signing packet or carry out an authorized signing step. Treat each as a separate request.

Workers return results to the parent, who handles user delivery. Dreamers use this skill for research only.

Review or prepare

  • Start with what the user asked. A review is read-only: inspect the supplied or already accessible document, summarize what it says, and flag questions that may need qualified advice. Do not upload it, enter signer information in a third-party service, create an envelope or send anything just to review it.
  • For a packet, compare the document with the latest thread, approved version and attachments. Check names, title, signing roles, recipient order, dates and exhibits. Map each required field to a signer and page. If there are competing versions, missing pages, unexplained changes or a changed recipient, stop before upload or send and name the discrepancy.
  • Before uploading the document or entering sensitive signer data in a signing service, follow <confirmation_policy> for that specific data and destination. Until authorized, prepare a private field checklist or cover note. Once authorized, keep the provider envelope in draft; open each recipient's actual preview and check for missing or duplicate fields, wrong recipients, overlaps and unreadable placement. Check mobile preview when available.
  • Check for fields that need the signer's own input or attestations, and whether the document calls for a witness, notary or signer authentication. Flag these without filling, bypassing or claiming to verify them. Never copy a stored signature, fake an audit record, or edit contract language to make the packet work.
  • Identify deadlines and what each signer still needs to do. Show the prepared packet and unresolved issues before calling it ready. Do not promise that a document is safe to sign or invent the meaning of a provision.
  • Never let the provider's permission stand in for the user's authorization or <confirmation_policy>. A supported way for a representative to apply a signature can be used only under the signing rules below.

Read the full file on GitHub · 75 lines

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. 12d ago First seen · 75 lines · 28 tokens per session scan A 0a3e44adc7d7

Subscribe to this mod's changes

document-signing is a skill published in the GitHub repository asgeirtj/system_prompts_leaks (69,821 stars, last pushed 2d ago), licensed CC0-1.0. It adds 28 tokens to every session and 1,257 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 2026-10-06.