Borrowing it
Nothing to install: this file belongs to yutakobayashidev/ava. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/yutakobayashidev/ava/main/.claude/skills/ava-mcp-usage/SKILL.mdgit clone --depth 1 https://github.com/yutakobayashidev/avaWrote 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/yutakobayashidev/ava/ava-mcp-usage)<a href="https://agentmods.dev/skills/yutakobayashidev/ava/ava-mcp-usage"><img src="https://agentmods.dev/badge/skills/yutakobayashidev/ava/ava-mcp-usage/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/yutakobayashidev/ava/ava-mcp-usage"><img src="https://agentmods.dev/badge/skills/yutakobayashidev/ava/ava-mcp-usage.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 | $0.00063 | $0.00867 |
| Opus 5.5 | $0.00025 | $0.00347 |
| Sonnet 5.5 | $0.00013 | $0.00173 |
| Haiku 4.5 | $0.00006 | $0.00087 |
Grade A, and why
ava-mcp-usage 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 — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ava MCP Usage
Overview
Ava provides MCP tools for automatic progress reporting to Slack. This skill shows you how to use these tools effectively with minimal mental burden while maintaining privacy.
Core Philosophy
Ava works best when you tell it what to watch: "Keep an eye on this work."
Important: Treat any coding work as a task, even if the user doesn't explicitly say "task". When the user starts working on something, that's a task to track.
Key principles:
- Treat all coding work as tasks worth tracking
- Report only the current task
- Proactive, frequent updates: Report progress at every meaningful milestone without waiting for user prompts
- Update granularly: schema changes, file edits, endpoint implementations, test additions - all worth reporting
- Ask for help immediately when blocked
- Ask user for consent before marking tasks complete
- Short commands are sufficient
- One task per session: If starting different work while a task is active, ask the user if they want to complete the current task first or start a new Claude Code session for the new work
MCP Tools Quick Reference
start_task
Tell Ava what you're working on now. Treat any coding work as a task, even if not explicitly called a "task".
Start task: ログインのエラー処理改善
Tips:
- Treat all coding work as tasks worth tracking
- Only report the task you're currently working on
- Be specific but concise
- Ava will create a Slack thread for this task
- Before starting a new task: If there's already an active task in this session, ask the user: "Should I complete the current task first, or would you like to start a new Claude Code session for this different work?"
update_task
Report progress proactively at every meaningful milestone, even without user prompts.
Update task: リトライ実装が完了
When to update (proactively):
- After creating or editing a schema file
- After implementing an endpoint or API route
- After adding validation logic
- After writing tests
- After fixing a bug or error
- After refactoring a component
- Any other meaningful progress point
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 · 131 lines · 63 tokens per session scan A cd69bd757cbb
ava-mcp-usage is a skill published in the GitHub repository yutakobayashidev/ava (9 stars, last pushed 6mo ago), licensed MIT. It adds 63 tokens to every session and 867 once invoked, about $0.0003 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 2026-08-31.
ava-mcp-usage compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| ava-mcp-usageyutakobayashidev/ava | Skill | 9 | 6mo ago | MIT | A | 63 | Claude Code |
| sugar-orchestratorroboticforce/sugar | Skill | 100 | yesterday | none | A | 103 | Claude Code |
| sugar-task-plannerroboticforce/sugar | Skill | 100 | yesterday | none | A | 112 | Claude Code |
| sugar-quality-guardianroboticforce/sugar | Skill | 100 | yesterday | none | A | 104 | Claude Code |
| sugar-memoryroboticforce/sugar | Skill | 100 | yesterday | none | A | 70 | Claude Code |
| canvashoainho/podium-mcp | Skill | 6 | 4mo ago | MIT | A | 61 | Claude Code |
| bug-reprohoainho/podium-mcp | Skill | 6 | 4mo ago | MIT | A | 42 | Claude Code |