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 minhnv0807/ai-business-skills --skill 67-agency-vendor-brief-globalgit clone --depth 1 https://github.com/minhnv0807/ai-business-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/minhnv0807/ai-business-skills/67-agency-vendor-brief-global)<a href="https://agentmods.dev/skills/minhnv0807/ai-business-skills/67-agency-vendor-brief-global"><img src="https://agentmods.dev/badge/skills/minhnv0807/ai-business-skills/67-agency-vendor-brief-global/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/minhnv0807/ai-business-skills/67-agency-vendor-brief-global"><img src="https://agentmods.dev/badge/skills/minhnv0807/ai-business-skills/67-agency-vendor-brief-global.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 160 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00166 | $0.02379 |
| Opus 5.5 | $0.00066 | $0.00952 |
| Sonnet 5.5 | $0.00033 | $0.00476 |
| Haiku 4.5 | $0.00017 | $0.00238 |
Grade A, and why
67-agency-vendor-brief-global 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 — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agency and Vendor Brief (Global)
Agencies usually deliver the wrong thing not because they are bad, but because the brief was thin and expectations never matched. A good brief means fewer revisions, on time, on budget. Treat the vendor as a professional partner rather than hired hands: a clear brief plus clear feedback produces the best work.
Information gathering
Read the campaign brief (02-campaign-brief-global) and the asset list (41-campaign-asset-list-global) if available. If missing, ask up to 4 questions:
- What exactly are you hiring for? Video production, design, media buying, PR, creator booking, landing page development?
- Timeline and hard deadline? Start date and the date the final must exist.
- Approved budget in USD? Is tax included, and what are the payment terms (net 15, net 30, milestone-based)?
- What specific deliverables must you receive, and who is the single point of contact on your side?
Principles
- Always brief in writing. No matter how good the relationship, a verbal brief gives you nothing to point at in a dispute.
- Feedback comes from ONE person. Multiple simultaneous reviewers confuse the vendor and stretch revision cycles.
- Fix the number of included revision rounds. Unlimited revisions disrespects both sides' time.
- State what is NOT included. This is the only reliable way to stop scope creep.
- Pay by milestone. Never pay 100% before work starts.
- Score the vendor after every project. Build an internal database so the next selection is fast and correct.
Workflow
1. Prepare before sourcing
Lock four things: a measurable project objective, a budget ceiling, a hard deadline, and the minimum acceptable deliverable. If those four are not clear, you are not ready to brief an agency.
2. Write and send the brief
Use the template below. Send it with the brand guideline, the brand voice document, and 3-5 good references plus the references you do not want.
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 First seen · 189 lines · 166 tokens per session scan A 44d05c036838
67-agency-vendor-brief-global is a skill published in the GitHub repository minhnv0807/ai-business-skills (618 stars, last pushed 1mo ago), licensed MIT. It adds 166 tokens to every session and 2,379 once invoked, about $0.0007 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
honcho
Configure and troubleshoot Honcho memory for Hermes.
pinecone-research
Agent RAG and long-term memory with Pinecone.
self_awareness
Ground self-referential answers in the agent's actual filesystem. Use when the user asks who the agent is, what it can do, what it knows, what it remembers, what it has built, what services are connected, or what rules it follows.
llm-wiki
Karpathy's LLM Wiki: build/query interlinked markdown KB.
qmd
Hybrid local search over notes, docs, and transcripts.
forget
Remove a personal fact, preference, relationship detail, topic, or prior event from Muse's active memory and stop existing copies or automations from bringing it back. Use for explicit requests such as 'forget that', 'don't remember this about me', or 'remove that from your memory'. Do not use when 'forget it' merely…