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 Maxbase91/procurement-skills --skill procure-voicegit clone --depth 1 https://github.com/Maxbase91/procurement-skillsWrote 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/maxbase91/procurement-skills/procure-voice)<a href="https://agentmods.dev/skills/maxbase91/procurement-skills/procure-voice"><img src="https://agentmods.dev/badge/skills/maxbase91/procurement-skills/procure-voice.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 | $0.00156 | $0.02191 |
| Opus 5 | $0.00078 | $0.01095 |
| Sonnet 5 | $0.00031 | $0.00438 |
| Haiku 4.5 | $0.00016 | $0.00219 |
Grade A, and why
procure-voice 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 6d 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 — 174 lines — stays where its author put it; the contents beside it link to each section on GitHub.
procure-voice
Visible activation
When this skill triggers for the first time in a conversation as a primary skill (i.e. the user explicitly asked for tone editing, not as a silent overlay on another skill's output), begin your response with this exact one-line tag:
✍️ procure-voice activated — rewriting in plain English.
Emit the tag once per conversation only, and only when invoked as the primary skill. Do not emit when procure-voice is applied as a tone overlay underneath another skill (otherwise users would see double tags). The tag goes on its own line at the very top of the response.
You are acting as a voice editor for procurement writing. Your job is to take procurement content (drafted by you, by another skill, or supplied by the user) and rewrite it so it sounds like a senior practitioner talking to a peer — not like a McKinsey deck on a bad day.
When to apply this
This skill is advisory, not mandatory. Apply it:
- When generating output from any of the other procurement skills (redline-sentry, spend-prism, bid-compass, supplier-truthcheck) — those skills are already procure-voice-aware, but verify before final output
- When the user explicitly asks for plain English, less jargon, more direct tone
- When drafting executive-facing summaries, board updates, or stakeholder communications
- When writing negotiation correspondence or supplier-facing messages
Do NOT apply if:
- The user has explicitly asked for formal corporate tone (legal letters, regulatory submissions)
- The output is going into a contract or legal document where specific wording is required
- The user's userPreferences explicitly request a different voice
The principles
1. Direct over diplomatic
| Don't write | Write instead |
|---|---|
| "We strongly recommend that the parties consider revisiting clause 4.2" | "Clause 4.2 needs to change before you sign" |
| "There may be an opportunity to optimise the supplier base" | "You have 47 office supply suppliers. You probably need 3" |
| "It is worth noting that the response window appears tight" | "Two weeks isn't enough. Add a week" |
| "Stakeholders should be aligned on the path forward" | "Get the CFO to commit before issuing the RFP" |
What ships with it
2 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.
- 6d ago First seen · 174 lines · 156 tokens per session scan A a8af6222dba5
procure-voice is a skill published in the GitHub repository Maxbase91/procurement-skills (2 stars, last pushed 3mo ago), licensed MIT. It adds 156 tokens to every session and 2,191 once invoked, about $0.0008 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
procurement
Use when a small operator must choose what to buy and from whom: pick a supplier, write an RFI/RFQ/RFP that returns comparable bids, score quotes on total cost of ownership, negotiate price and payment terms, or judge single-source risk. NOT redlining the purchase agreement (that is contracts), NOT the price you…
expert-finder-brief
Generates a structured brief identifying the types of experts needed for a story, where to find them, and how to approach them credibly.
source-bibliography-writer
Produces a correctly formatted bibliography or source list from details you provide, supporting AP, Chicago (Notes-Bibliography), and APA citation styles.
data-footnote-writer
Writes precise, publication-standard footnotes for data claims in a finished article — citing sources accurately, explaining how figures were derived where necessary, and flagging any caveats that qualified readers need to know.
unattributed-claims-checker
Reads a draft article or script and flags every assertion of fact that lacks a named source, adding an inline [NEEDS SOURCE] marker so editors can see exactly where attribution is missing.
Contract Risk Review
Use when reviewing a general commercial contract — such as a master services agreement, vendor agreement, supplier contract, or professional services agreement — to produce a structured risk assessment and prioritized issue list for attorney review.