Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/mishahanin/heading-osnpx agentmods add skills/mishahanin/heading-os/partnership-docWrote 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/mishahanin/heading-os/partnership-doc)<a href="https://agentmods.dev/skills/mishahanin/heading-os/partnership-doc"><img src="https://agentmods.dev/badge/skills/mishahanin/heading-os/partnership-doc/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/mishahanin/heading-os/partnership-doc"><img src="https://agentmods.dev/badge/skills/mishahanin/heading-os/partnership-doc.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 | $0.00116 | $0.01647 |
| Opus 5.5 | $0.00046 | $0.00659 |
| Sonnet 5.5 | $0.00023 | $0.00329 |
| Haiku 4.5 | $0.00012 | $0.00165 |
Grade A, and why
partnership-doc 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 1mo 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 — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Partnership Document (MOU / LOI / Term Sheet)
Produce a locked 31C partnership document. Use for legal-adjacent collaboration frameworks. For commercial pricing and module activation, use /proposal instead.
Variables
subtype: one ofMemorandum of Understanding/Letter of Intent/Term Sheet/Partnership Agreementcounterparty: the other party's legal name, jurisdiction, and addressscope: territory, duration, exclusivity posturecommercial_outline: margin structure, payment terms (non-binding for MOU/LOI, binding for term sheet)governance: dispute resolution preference
Phase 0: Context Loading
Read:
reference/corporate-style-guide.md- locked template, checklist, terminology.claude/rules/corporate-docs.md- guardrail.claude/rules/terminology.md,.claude/rules/voice.md,.claude/rules/voss.mdstatus/entity/context/partners.md,status/matter/context/pipeline.md- existing relationship statecanon/reference/reference/billion-growth-playbook.md- channel economics where relevant
Phase 1: Classify and Confirm
Announce:
Using
/partnership-doc({subtype} template). PDF + DOCX will be rendered. Locked parties block, clause structure, signature grid, and confidentiality applied.
Clarify any of these before drafting:
- Subtype (MOU vs LOI vs term sheet) - they differ in binding scope.
- Counterparty's full legal name, entity type, jurisdiction, principal office address.
- Authorised signatory name and title on both sides.
- Territory and term.
- Exclusivity posture.
- Governance and dispute resolution jurisdiction preference.
Phase 2: Draft Clauses
Voice: neutral legal-adjacent, not marketing prose. No Voss negotiation moves inside the document - those belong in the cover letter and negotiation playbook, not the executed text.
Default clause set:
- Territory
- Exclusivity (grant, carve-outs, minimum performance)
- Commercial terms (margin, payment days, term length)
- Training and certification
- Marketing and brand use
- Data protection and sovereignty
What ships with it
3 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.
- 1mo ago Changed · +15 lines dd7d852931c7
- 1mo ago Changed · +1 lines ebaa8b0784c3
- 1mo ago First seen · 136 lines · 116 tokens per session scan A 65f6a8851b3e
partnership-doc is a skill published in the GitHub repository mishahanin/heading-os (11 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 116 tokens to every session and 1,647 once invoked, about $0.0005 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 2026-09-03.
Other skills, from other repositories
PDF files: create, read, merge, fill, OCR, edit text.
meta-pdf-reformat-pipeline
Modernize a legacy PDF: structural extraction → natural-language rewrite of problem pages → audit summary → re-merge into the final PDF.
pdf-text-replace
Replace text in fillable PDF forms by updating form field values. This skill should be used when users need to update names, addresses, dates, or other text in PDF form fields.
audit-export
Export the full CocoAudit trail as a stakeholder-ready compliance document.
Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and…
tageszeitung
Creates a personalised daily newspaper from RSS feeds and web sources. Ported from the BACH news system (news.py + newspapergenerator.py). Own SQLite store (no Origin-DB). feedparser optional — XML fallback via stdlib. PDF export via Edge Headless (msedge.exe).