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 arunbalajiraju-proc/procurement-ai-assistant --skill procurement-intake-skillgit clone --depth 1 https://github.com/arunbalajiraju-proc/procurement-ai-assistantWrote 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/arunbalajiraju-proc/procurement-ai-assistant/procurement-intake-skill)<a href="https://agentmods.dev/skills/arunbalajiraju-proc/procurement-ai-assistant/procurement-intake-skill"><img src="https://agentmods.dev/badge/skills/arunbalajiraju-proc/procurement-ai-assistant/procurement-intake-skill/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/arunbalajiraju-proc/procurement-ai-assistant/procurement-intake-skill"><img src="https://agentmods.dev/badge/skills/arunbalajiraju-proc/procurement-ai-assistant/procurement-intake-skill.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00034 | $0.02108 |
| Opus 5.5 | $0.00014 | $0.00843 |
| Sonnet 5.5 | $0.00007 | $0.00422 |
| Haiku 4.5 | $0.00003 | $0.00211 |
Grade A, and why
procurement-intake-skill 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 2mo 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 — 363 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill Name
Procurement Intake and Triage Skill
Purpose
This skill helps AI review an incoming procurement request before a sourcing strategy is selected.
Use it to separate the underlying business need from a proposed solution, identify missing information, classify risk and complexity, prepare stakeholder questions, and recommend possible next steps for human consideration.
This skill does not approve a purchase, choose a sourcing method, authorize a supplier, interpret policy as final authority, or replace procurement judgment.
Composability
This skill is standalone. If other Procurement AI Assistant skills are installed, the AI may combine relevant skills for a multi-step procurement request. Do not assume another skill is available; preserve this skill's own guardrails and human review points.
Core Principle
Do not automate an unclear request.
The workflow is:
Understand -> Separate Need from Solution -> Identify Gaps -> Classify -> Assess Risk -> Prepare Questions -> Present Options -> Human Decision
When to Use
Use this skill for:
- New procurement requests
- Renewal or extension requests
- Preferred-supplier requests
- Urgent or emergency requests
- SaaS or software intake
- Consulting or professional services intake
- Goods, services, managed services, and hybrid requirements
- Early sourcing strategy preparation
- Requests with unclear scope, budget, timeline, or ownership
- Requests that may involve privacy, security, accessibility, legal, or financial review
Do Not Use This Skill For
Do not use this skill to:
- Approve the request
- Select a sourcing method as a final decision
- Validate a sole-source justification as final
- Select or recommend a supplier for award
- Bypass competition, policy, approvals, or governance
- Invent requirements, budgets, timelines, or risk classifications
- Treat urgency as proof that competition is impossible
Required Inputs
Collect what is available from the following areas.
Business Need
- Problem or opportunity
- Desired outcome
- Users or beneficiaries
- Current process or solution
- Consequence of doing nothing
- Business criticality
What ships with it
1 file 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.
- 2mo ago First seen · 363 lines · 34 tokens per session scan A 61bf3c8d1a4f
procurement-intake-skill is a skill published in the GitHub repository arunbalajiraju-proc/procurement-ai-assistant (18 stars, last pushed 3mo ago), licensed MIT. It adds 34 tokens to every session and 2,108 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 2026-08-30.
procurement-intake-skill compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| procurement-intake-skillarunbalajiraju-proc/procurement-ai-assistant | Skill | 18 | 3mo ago | MIT | A | 34 | Claude Code, Codex |
| repomixyamadashy/repomix | Skill | 29k | today | MIT | A | 58 | Claude Code, Codex |
| google-agents-cli-scaffoldgoogle/agents-cli | Skill | 6.3k | 2d ago | Apache-2.0 | A | 135 | Claude Code |
| ti-yara-huntingPurpleAILAB/Decepticon | Skill | 6.5k | 8d ago | Apache-2.0 | A | 58 | Claude Code |
| ti-ioc-extractionPurpleAILAB/Decepticon | Skill | 6.5k | 8d ago | Apache-2.0 | A | 75 | Claude Code |
| m365-mailbox-compromisePurpleAILAB/Decepticon | Skill | 6.5k | 8d ago | Apache-2.0 | A | 45 | Claude Code, Codex |
| blind-sqliPurpleAILAB/Decepticon | Skill | 6.5k | 8d ago | Apache-2.0 | A | 88 | Claude Code, Codex |