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 jonathanung/finesse --skill uat-proceduregit clone --depth 1 https://github.com/jonathanung/finesseWrote 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/jonathanung/finesse/uat-procedure)<a href="https://agentmods.dev/skills/jonathanung/finesse/uat-procedure"><img src="https://agentmods.dev/badge/skills/jonathanung/finesse/uat-procedure.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 | $0.00022 | $0.00982 |
| Opus 5 | $0.00011 | $0.00491 |
| Sonnet 5 | $0.00004 | $0.00196 |
| Haiku 4.5 | $0.00002 | $0.00098 |
Grade A, and why
uat-procedure 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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
UAT Checkpoint Procedure
Phases marked [UAT] in the workflow sequences require a User Acceptance Testing checkpoint before proceeding. When you reach a [UAT] phase:
1. Present the phase output
Format the output for review using this structure:
UAT Checkpoint: [Phase Name]
- What was done: 1-2 sentence summary of the phase's activity
- Key findings / decisions: Bulleted list of substantive outputs (architecture choices, files identified, root cause hypothesis, etc.)
- Impact on next phases: How this output shapes what comes next
2. Ask the user
Use AskUserQuestion with these 4 options:
- Accept — proceed to the next phase
- Provide feedback — re-run this phase incorporating the user's free-text feedback
- Make specific changes — apply the user's targeted edits to the phase output without re-running
- Accept and skip remaining UAT — auto-approve all future UAT checkpoints in this planning session
3. Handle the response
- Accept: Proceed to the next phase.
- Provide feedback: The user gives free-text feedback. Snapshot the current phase output, then re-run the phase from scratch incorporating their feedback as additional constraints. Generate a diff summary comparing the pre-feedback and post-feedback phase output (see Diff Summary Format below). Present the revised output at the same UAT checkpoint again, with the diff summary included under a "What changed since last review:" heading above the phase output.
- Make specific changes: The user specifies targeted edits (e.g., "change the database from PostgreSQL to SQLite in the architecture"). Snapshot the current phase output, then apply the edits directly without re-running the full phase. Generate a diff summary comparing the pre-edit and post-edit phase output (see Diff Summary Format below). Present the revised output at the same UAT checkpoint again, with the diff summary included under a "What changed since last review:" heading above the phase output.
- Accept and skip remaining UAT: Note that UAT is fast-forwarded. For all subsequent
[UAT]phases, auto-accept and proceed without presenting the checkpoint. Discovery/Understanding phase confirmations are NOT affected by fast-forward — those always happen.
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 · 61 lines · 22 tokens per session scan A 1067ad905fd1
uat-procedure is a skill published in the GitHub repository jonathanung/finesse (4 stars, last pushed 6mo ago), licensed MIT. It adds 22 tokens to every session and 982 once invoked, about $0.0001 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
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
Cortex
Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
peekaboo
Capture and automate macOS UI with the Peekaboo CLI.
mochi-remind
Handle due reminders — notify the user with natural language and mark them done.