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 tkumata/AGENTS.md --skill issue-workflowgit clone --depth 1 https://github.com/tkumata/AGENTS.mdWrote 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/tkumata/agents.md/issue-workflow)<a href="https://agentmods.dev/skills/tkumata/agents.md/issue-workflow"><img src="https://agentmods.dev/badge/skills/tkumata/agents.md/issue-workflow/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/tkumata/agents.md/issue-workflow"><img src="https://agentmods.dev/badge/skills/tkumata/agents.md/issue-workflow.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 | $0.00060 | $0.00652 |
| Opus 5.5 | $0.00024 | $0.00261 |
| Sonnet 5.5 | $0.00012 | $0.00130 |
| Haiku 4.5 | $0.00006 | $0.00065 |
Grade A, and why
issue-workflow 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 18d 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.
What it actually says
Issue Workflow Skill
ユーザが issue-workflow を明示的に指定した場合のみ使用する。
Codex CLI / Codex Desktop App の既存セッション内で実行する。Codex を新規起動しない。
Workflow
- Issue を特定する。 非対話型 CLI の
~/.cargo/bin/gh-issues-triage next <owner/repo> --format jsonで開発候補を取得する。<owner/repo>は基本的にユーザが指定するが、ない場合は現在のプロジェクトから入手する。現在のプロジェクトから取得もできない場合は終了する。 - Issue を取得する。 取得した JSON から、タイトル、本文、ブランチ名の候補文字列を抽出する。JSON を取得できない場合は終了する。
- ブランチを作成する。 取得したブランチ名の候補文字列を使用して、ローカル上で新しいブランチを作成する。既存のブランチ名と重複する場合は、ユーザに通知して終了する。
- 文書化する。 取得したタイトルと本文を
brain-dump-docsスキルを使用して文書化する。 - 承認を得る。 作成・更新した文書、実装範囲、受け入れ条件、未決定事項を報告し、ユーザの承認を待つ。承認済み範囲の変更や不明点は既存のグローバル
AGENTS.mdの規則に従う。 - 実装する。 承認済み文書を参照して、現在の Codex セッションで実装する。独立した
codex execや新規セッションを起動しない。コード品質はグローバルAGENTS.mdに従う。
Boundaries
gh-issues-triageは Issue の選定・取得を担当し、Codex やスキルを起動しない。brain-dump-docsは開発文書の作成・更新を担当し、ソースコードを変更しない。issue-workflowは処理順序と承認境界だけを担当する。既存スキルと Stop hook の処理を重複実装しない。- 未決定事項を補完して実装判断しない。文書承認なしに実装を始めない。
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.
- 18d ago Changed 2d1451ae57a5
- 19d ago First seen · 28 lines · 60 tokens per session scan A 08ea7b65ddc6
issue-workflow is a skill published in the GitHub repository tkumata/AGENTS.md (1 stars, last pushed 11d ago), licensed MIT. It adds 60 tokens to every session and 652 once invoked, about $0.0002 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 2026-10-08.
Other skills, from other repositories
conductor-revert
Git-aware undo by logical work unit (track, phase, or task).
feature-execution
A feature-delivery coordinator that divides a feature into waves of work, assigns agents, manages review rounds, and commits each wave.
mcore-split-pr
Split a PR into multiple PRs to reduce the number of required CODEOWNERS reviewer groups.
engineer-bot-ops
A workflow for carrying an engineering task from scope through implementation and reviewable delivery. It works with a repository's branch, existing changes, rules, checks, and permissions while separating completed, unverified, and next-step work.
gait-session-tracking
GAIT session lifecycle management - branch creation, turn recording, audit logging for every NetClaw operation. Use when starting a new NetClaw session, recording a health check or config change, pinning a pre-change baseline, or viewing the audit trail for a troubleshooting session.
deliver-spec
Use when explicitly asked to deliver an approved GitHub or local spec through a reviewed pull request, or when a Project controller delegates one claimed implementation ticket.