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 masa-san-jp/Agent-Aiko --skill rolegit clone --depth 1 https://github.com/masa-san-jp/Agent-AikoWrote 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/masa-san-jp/agent-aiko/role)<a href="https://agentmods.dev/skills/masa-san-jp/agent-aiko/role"><img src="https://agentmods.dev/badge/skills/masa-san-jp/agent-aiko/role/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/masa-san-jp/agent-aiko/role"><img src="https://agentmods.dev/badge/skills/masa-san-jp/agent-aiko/role.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 | $0.00096 | $0.01135 |
| Opus 5 | $0.00048 | $0.00567 |
| Sonnet 5 | $0.00019 | $0.00227 |
| Haiku 4.5 | $0.00010 | $0.00113 |
Grade A, and why
role 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 9d 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/role
capability manifest を解決して、そのロールのコンテキストを現在のセッションに注入する role-switch resolver の参考実装。パス・ロール名は各組織の構成に合わせて調整して使う。
ロールは 1 つの capability manifest（purpose・required_skills・required_tools・原則・判断基準など）で定義される。このスキルはその manifest を読み込んでコンテキストとして注入するだけで、エージェント本体（人格 base）は切り替えない。
引数
/role <name> # 例：finance / hr / ops / sales / pr / research
/role list # 利用可能なロール一覧（manifest が存在するもの）
/role status # 現在アクティブなロール（最後に適用したもの）
実行手順
<name>の manifest を解決する。既定は{{ORG_REPO_PATH}}/Agent-team/roles/<name>/manifest.json。 エージェント固有のロールを持つ構成では{{ORG_REPO_PATH}}/Agent-team/agents/<agent>/capability/manifest.jsonを優先してよい（探索先は自組織の配置に合わせる）- purpose は manifest の
purpose、または manifest が指す operating-model ドキュメントから取る - 各
required_skillsエントリを解決する：skills/<entry>.md/skills/<entry>.py/skills/<entry>/SKILL.mdの順で最初に一致したもの required_toolsを{{ORG_REPO_PATH}}/Agent-team/tools/<tool>/配下で解決する（<tool>はツール名。ロール名<name>とは別のプレースホルダ）communication/common_principles/decision_criteria/prohibitions/imported_capabilitiesはコンテキストとして扱う- 切替イベントを
{{ORG_REPO_PATH}}/Agent-team/logs/role-events/<role>/YYYY-MM-DD.jsonlに 1 行追記する
注入フォーマット
切替時、以下を内部コンテキストとして扱う（ユーザーへの報告は「切り替えました」を 1〜2 行のみ）：
[role: <name>]
purpose: <manifest の purpose または operating-model の要約>
manifest_file: <解決された manifest のパス>
communication: <manifest communication>
common_principles: <manifest common_principles>
decision_criteria: <manifest decision_criteria>
prohibitions: <manifest prohibitions>
imported_capabilities: <manifest imported_capabilities>
required_skills:
- <skill1>: <SKILL.md description の先頭 80 文字>
- <skill2>: ...
required_tools:
- <tool1>: <tools/<tool>/README.md の先頭 80 文字（あれば）>
切替報告（ユーザー向け）
ロール "<name>" に切り替えました。
- Required skills: <件数>（例：agent-call / log-push / ...）
- Required tools: <件数>（例：agent-call / peer-inbox / ...）
- Purpose: <manifest からの 1 行要約>
制約
- 人格 base 不変：人格の切替とは独立。ロールのコンテキストを注入するだけで、人格そのものは切り替えない
- データスコープはエージェントに従う：各エージェントは自分の data root を保持し、このスキルはそれを変更しない
- 再帰禁止：切替後にさらに別ロールへ切り替えたい場合は新しいセッションを推奨（コンテキストを clean に保つ）
- エラー処理：manifest が無い、または
required_skillsが解決できない場合は切替を中止し、何が欠けているかを報告する
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.
- 9d ago First seen · 71 lines · 96 tokens per session scan A 5967fdedef57
role is a skill published in the GitHub repository masa-san-jp/Agent-Aiko (3 stars, last pushed 1mo ago), licensed MIT. It adds 96 tokens to every session and 1,135 once invoked, about $0.0005 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
share-skills
Use when you need to author, package, or share a skill folder — understanding the SKILL.md format, where skills live, and how to bundle a folder so it can be shared with others.
git-commit
Stage, write, and structure git commits and pull requests cleanly. Read this before committing — for conventional-commit message format, when to split commits, and how to open a PR with the gh CLI.
openai-whisper-api
Transcribe audio via OpenAI Audio Transcriptions API (Whisper).
app_evaluator
A professional skill for App Evaluation (evaluating app's performance with score) and App Improvement (giving professional suggestions for improving the app's performance).
add-backend
Guide for adding a backend (Rust or Python) to the agent-sec-core security middleware. Use when creating new backends, integrating Rust or Python code into the security middleware, or extending with new backend actions.
skill-ledger
A security record for agent skills, which are reusable instruction packages for coding agents. It shows their status, reviews risk exposure, and can certify them with quick or user-approved deeper scans.