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 MarcoZorn/agencykit --skill client-approvalgit clone --depth 1 https://github.com/MarcoZorn/agencykitWrote 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/marcozorn/agencykit/client-approval)<a href="https://agentmods.dev/skills/marcozorn/agencykit/client-approval"><img src="https://agentmods.dev/badge/skills/marcozorn/agencykit/client-approval.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 | $0.00041 | $0.02545 |
| Opus 5 | $0.00020 | $0.01273 |
| Sonnet 5 | $0.00008 | $0.00509 |
| Haiku 4.5 | $0.00004 | $0.00254 |
Grade A, and why
client-approval 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 7d 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 — 196 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Client Approval
When to use this skill
English: "approval", "get client feedback", "send for review", "revision request", "waiting on client", "chase the client".
Italiano: "approvazione", "revisione", "feedback cliente", "in attesa cliente", "manda in approvazione".
What this skill does
Produces everything you need to move a deliverable through client sign-off without it disappearing into a WhatsApp thread: a clean client-facing approval message, an internal note that sets an SLA and an escalation trigger, and a PM-tool status line. It also counts revision rounds and warns you the moment a revision crosses from "included" into "billable extra" — the money most agencies quietly give away.
Inputs required
- Deliverable — what is being approved (reel, carousel, draft, design, cut).
- Client name and the contact who signs off.
- Which revision round is this — first send, revision 1, revision 2, revision 3+? If you do not say, the skill infers it from the conversation history and states its assumption.
- Included revisions in the contract — default is 2 if you do not specify.
- Deadline you need it back by — used to set the SLA.
Output format
Three blocks:
- CLIENT MESSAGE — polished, warm, professional. Ready to send as-is.
- INTERNAL NOTE — SLA, escalation trigger, revision count and billing flag. Never send this to the client.
- PM STATUS — a one-line status update for Asana / ClickUp / Notion.
Human gate
This output is a draft. Review SLA, revision count, and all commitment language before sending to the client. The skill surfaces the judgment call — a person signs off.
Brand voice
If a BRAND.md file exists in this skill's folder (.claude/skills/client-approval/BRAND.md) or in .claude/brand/BRAND.md (global fallback), read it before generating output and apply its tone, terminology, and examples to all text you produce. A skill-local BRAND.md overrides the global one; if neither exists, use a clean, professional default voice.
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.
- 7d ago First seen · 196 lines · 41 tokens per session scan A 30cc3b0511b0
client-approval is a skill published in the GitHub repository MarcoZorn/agencykit (6 stars, last pushed 2mo ago), licensed MIT. It adds 41 tokens to every session and 2,545 once invoked, about $0.0002 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
workflow-run
Use when you need to execute a DAG-structured workflow template from SKILLS/ORCHESTRATION FRAMEWORK/workflow-templates/.
multi-agent
A process for coordinating multiple coding agents by splitting work among scouts, workers, reviewers, and repair agents. Each agent has a defined role and task.
omh-research-department
This is a Hermes-native research-department workflow skill.
omh-agent-board
This is a Hermes-native agent-board workflow skill.
omh-cto-loop
This is a Hermes-native cto-loop workflow skill.
triage-sweep
Backfill labels across oh-my-hermes issues and pull requests. Run manually to sweep everything currently unlabeled, or pass a number to triage one item. Use when issues and PRs have accumulated without labels, after adding a new label to .github/labels.yml, or before a release when the backlog needs to be readable by…