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 agentmods add skills/psd401/psd-claude-plugins/documenso-managernpx skills add psd401/psd-claude-plugins --skill documenso-managergit clone --depth 1 https://github.com/psd401/psd-claude-pluginsWrote 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/psd401/psd-claude-plugins/documenso-manager)<a href="https://agentmods.dev/skills/psd401/psd-claude-plugins/documenso-manager"><img src="https://agentmods.dev/badge/skills/psd401/psd-claude-plugins/documenso-manager.svg" alt="Measured on agentmods" 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 | $0.00080 | $0.03137 |
| Opus 5 | $0.00040 | $0.01569 |
| Sonnet 5 | $0.00016 | $0.00627 |
| Haiku 4.5 | $0.00008 | $0.00314 |
Grade A, and why
documenso-manager 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.
How it starts
The opening of the file, as written. The whole thing — 218 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Documenso Manager
Configuration
- Server: Read from
DOCUMENSO_HOSTenvironment variable (never hardcoded) - API Auth:
Authorization: api_xxxxxxxxheader (NOT Bearer — literal key value) - API Version: v2 only (v1 is deprecated)
- MCP: Official Documenso SDK MCP server for document/template discovery
- Scripts:
plugins/psd-productivity/skills/documenso-manager/scripts/
All scripts use bun and read credentials from secrets.js (env vars → Geoffrey .env).
Command Reference
Envelope Management
| Command | Script | Description |
|---|---|---|
/documenso status |
bun health_check.js |
Server health, envelope count |
/documenso list |
bun list_envelopes.js |
List all envelopes |
/documenso list '{"status":"PENDING"}' |
bun list_envelopes.js '{"status":"PENDING"}' |
Filter by status |
/documenso show <id> |
bun get_envelope.js <id> |
Envelope details (recipients, fields, items) |
/documenso create <pdf> [options] |
bun create_envelope.js <pdf> '<json>' |
Create envelope with PDF |
/documenso update '<json>' |
bun update_envelope.js '<json>' |
Update envelope metadata |
/documenso delete <id> |
bun delete_envelope.js <id> |
Delete envelope (confirm first) |
/documenso duplicate <id> |
bun duplicate_envelope.js <id> |
Clone an envelope |
Distribution & Download
| Command | Script | Description |
|---|---|---|
/documenso send <id> |
bun distribute_envelope.js <id> |
Send for signing (DRAFT → PENDING) |
/documenso resend <id> |
bun redistribute_envelope.js <id> |
Resend signing emails |
/documenso download <item-id> |
bun download_document.js <item-id> signed |
Download signed PDF |
/documenso download <item-id> original |
bun download_document.js <item-id> original |
Download original PDF |
/documenso audit <id> |
bun get_audit_log.js <id> |
Audit trail |
Recipients & Fields
| Command | Script | Description |
|---|---|---|
/documenso add-recipients <id> '<json>' |
bun add_recipients.js <id> '<json>' |
Add recipients (SIGNER/APPROVER/CC/VIEWER/ASSISTANT) |
/documenso update-recipients <id> '<json>' |
bun update_recipients.js <id> '<json>' |
Update recipients |
/documenso remove-recipient <id> <rid> |
bun remove_recipient.js <id> <rid> |
Remove recipient |
/documenso add-fields <id> '<json>' |
bun add_fields.js <id> '<json>' |
Add fields (SIGNATURE/DATE/TEXT/etc.) |
/documenso update-fields <id> '<json>' |
bun update_fields.js <id> '<json>' |
Update field positions |
/documenso remove-field <id> <fid> |
bun remove_field.js <id> <fid> |
Remove field |
What ships with it
29 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.
- references/documenso-api-reference.md 9.4 KB
- references/documenso-envelope-lifecycle.md 6.4 KB
- references/documenso-self-hosting-ops.md 7.6 KB
- references/psd-signing-templates.md 5.3 KB
- references/psd-signing-workflows.md 3.6 KB
- scripts/add_fields.js 1.8 KB runs code
- scripts/add_recipients.js 1.3 KB runs code
- scripts/create_envelope.js 2.4 KB runs code
- scripts/create_folder.js 621 B runs code
- scripts/delete_envelope.js 1.0 KB runs code
- scripts/distribute_envelope.js 1007 B runs code
- scripts/documenso_client.js 1.6 KB runs code
- scripts/documenso-mcp-proxy.sh 1.3 KB runs code
- scripts/download_document.js 1.7 KB runs code
- scripts/duplicate_envelope.js 902 B runs code
- scripts/get_audit_log.js 617 B runs code
- scripts/get_envelope.js 763 B runs code
- scripts/get_template.js 603 B runs code
- scripts/health_check.js 740 B runs code
- scripts/list_envelopes.js 1.7 KB runs code
- scripts/list_folders.js 417 B runs code
- scripts/list_templates.js 1.1 KB runs code
- scripts/redistribute_envelope.js 767 B runs code
- scripts/remove_field.js 756 B runs code
- scripts/remove_recipient.js 800 B runs code
- scripts/update_envelope.js 1013 B runs code
- scripts/update_fields.js 1011 B runs code
- scripts/update_recipients.js 1.1 KB runs code
- scripts/use_template.js 1.5 KB runs code
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 · 218 lines · 80 tokens per session scan A e120d0291d74
documenso-manager is a skill published in the GitHub repository psd401/psd-claude-plugins (2 stars, last pushed 4d ago), licensed MIT. It adds 80 tokens to every session and 3,137 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
meta-pdf-reformat-pipeline
Modernize a legacy PDF: structural extraction → natural-language rewrite of problem pages → audit summary → re-merge into the final PDF.
patent-reader
中国专利通俗解读：公开号/PDF 成通俗笔记、图谱与 Obsidian 入库。.
software-copyright-materials
Generate guided Chinese software copyright application materials from a real project. Use this skill when the user asks for 软件著作权, 软著申请资料, 软著代码材料, 操作手册, 申请表信息, or wants Word/TXT materials for software copyright registration. The workflow analyzes the imported project, extracts real source code, creates Markdown drafts…
ectd-xml-compiler
Automatically convert uploaded drug application documents (Word/PDF) into XML skeleton structure compliant with eCTD 4.0/3.2.2 specifications.
audit-export
Export the full CocoAudit trail as a stakeholder-ready compliance document.
software-certificate-skill
面向普通用户，从真实软件项目全自动生成中国软件著作权申请资料：一次收集登记事实，自动分析业务、选择可追溯源码、取得真实界面证据，生成申请表信息、规范黑白灰操作手册、代码前后30页或全部材料及真实 DOCX/PDF；内部验证、渲染、哈希与备份只进入系统临时运行区，项目最终仅保留正式资料。适配 Codex、Claude Code、Cursor、OpenCode、WorkBuddy、QoderWork、TraeWork 及支持 Agent Skills 或 AGENTS.md 的平台。用户提到软件著作权、软著申请资料、申请表、代码材料、操作手册或软著审查时使用。.