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 miyatti777/ai-plc --skill aipm-guidedgit clone --depth 1 https://github.com/miyatti777/ai-plcWrote 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/miyatti777/ai-plc/aipm-guided)<a href="https://agentmods.dev/skills/miyatti777/ai-plc/aipm-guided"><img src="https://agentmods.dev/badge/skills/miyatti777/ai-plc/aipm-guided/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/miyatti777/ai-plc/aipm-guided"><img src="https://agentmods.dev/badge/skills/miyatti777/ai-plc/aipm-guided.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 | $0.00073 | $0.09758 |
| Opus 5.5 | $0.00029 | $0.03903 |
| Sonnet 5.5 | $0.00015 | $0.01952 |
| Haiku 4.5 | $0.00007 | $0.00976 |
Grade A, and why
aipm-guided 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 2d 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 — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AIPMの形式で一歩ずつ進める
この AIPM モードが扱う範囲
- 扱う：立ち上げの工程（3つのコースとも、1人の利用者について課題→仮説検証→解決策→ストーリーまで）で作る19文書と、その内部保存
- 扱う（箱の中の操作）：論点・仮説・ToDo の1件の操作と、会議・FB の後の取込（下の「箱の中の操作（pm-）」。「案件側の一覧」を選んだ案件だけ）、19文書の改訂の範囲の案（書き換えはしない）
- 扱わない（今は無い）：日次・週次の締めと見直し、フェーズ・契約・PJ の終了時の引継ぎ
- 「AIPM」と呼ぶ別の仕組みとは、名前が同じでも中身が同じとは限らない。この AIPM モードを入れたことを、別の仕組みの置き換え・統合と扱わない。日次・週次の締めや引継ぎについて聞かれたら、このモードでは扱わないと答える（会議の後の取込は pm-capture、今日の1件は pm-today）
本人が対象LayerでAIPMを明示選択したときだけ intent.yaml の addons に同梱の1件（addon_id: aipm・source: bundled）を保存する（新しい Layer に work_style は書かない。旧い Layer の work_style: aipm は同じに読む）。引用・過去の報告・候補としての説明は選択ではない。未指定/nullは従来経路、保存値は勝手に補わない。mode のdirect/platform_builder、Role、深度、通常/auto/forceの権限は共通正本のまま。子への強制伝播や既存Layer一括更新はしない。選択解除はPMの選択を両方の欄（addons の同梱の1件と旧い欄）から外し、文書を保持する。
同梱アドオンとしての扱い
このスキルは同梱の PM アドオンとして目録（addon-catalog.yaml の aipm）に載る。選んだときは addons に同梱の1件を書く（上の段落）。旧い Layer の work_style: aipm は目録の legacy_alias で、判定関数 .claude/skills/ai-plc/scripts/plc_addon_select.py が同梱の aipm を選んだものとして読む（intent は書き換えない。一括の移行はしない）。aipm: の設定（course・registers・storage・stock_selector など）と mode_init の置き場・意味は変えず、addons の1件の中へ移さない。同梱の aipm は addon_init を使わない。
正本・入力
固定版はlivyn-inc/aipm-commands commit 2a7cdb8a77cb1b20e1325649faac0d7f177afb62。原文5コマンド、19raw templates、形式schemaのhashを確認する。これは元のCursorコマンドをAI-PLCへ接続した手順で、原文シェルをそのまま実行しない。利用者は本人/Contextから理解し、架空属性やインタビューを補完しない。
既存探索型は question_based/single_persona、Init→ペルソナ→課題→仮説検証→解決策→ストーリー→内部保存。この順序・19成果・本人判断を維持する。単一利用者向けにsolution_based/single_personaとdocument_based/single_personaのローカル拡張を追加し、下記の別生成契約を使う。多人数分岐や05以降の文書生成は未対応。
aipm は任意map: program_id / project_id / date（YYYY-MM-DD）/ persona_id（P001等）/ name_slug / course。未指定のIDは既存scope_id/scope_name、personaはP001、slugはuser。識別子はASCIIの英数字/ハイフン/underscoreだけ。日本語scope_nameなら明示project_idを設定する。人物属性をこの識別子から推測しない。保存場所は固定 Documents/aipm_project、その内部だけにFlow/Stockを作る。別Registry Projectは登録しない。share値はdisabled。
What ships with it
47 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- canonical.yaml 267 B
- course_contracts.yaml 1.2 KB
- format_schema.yaml 24 KB
- ops.py 32 KB runs code
- ops/capture.md 2.3 KB
- ops/hypothesis.md 2.7 KB
- ops/init.md 3.0 KB
- ops/issue.md 3.4 KB
- ops/persona.md 2.2 KB
- ops/story.md 2.1 KB
- ops/today.md 1.6 KB
- ops/todo.md 2.4 KB
- package.py 69 KB runs code
- registers_contract.v1.yaml 6.7 KB
- registers_contract.yaml 8.5 KB
- rollback.py 2.9 KB runs code
- source/0_initialize/00_プロジェクト開始.md 12 KB
- source/3_discovery/01_ペルソナ作成.md 30 KB
- source/3_discovery/02_課題定義.md 35 KB
- source/3_discovery/03_ソリューションマップ.md 35 KB
- source/3_discovery/04_ストーリーマップ.md 20 KB
- source/source_manifest.json 3.4 KB
- templates/create_stock_readme.txt 708 B
- templates/export_customer_problem_map_mermaid.txt 451 B
- templates/export_customer_problem_map_yaml.txt 1.6 KB
- templates/export_problem_map_mermaid.txt 628 B
- templates/export_problem_map_yaml.txt 925 B
- templates/export_solution_map_mermaid.txt 592 B
- templates/export_solution_map_yaml.txt 761 B
- templates/export_story_map_mermaid.txt 376 B
- templates/export_story_map_yaml.txt 910 B
- templates/export_viewer_integrated_yaml_final.txt 1.6 KB
- templates/generate_experience_mermaid.txt 1.9 KB
- templates/generate_experience_yaml.txt 1.3 KB
- templates/generate_integrated_experience_map.txt 1.5 KB
- templates/generate_persona_md.txt 1.2 KB
- templates/generate_personas_summary.txt 2.8 KB
- templates/generate_problem_statement.txt 347 B
- templates/generate_solution_map.txt 629 B
- templates/generate_story_map_md.txt 568 B
- templates/write_init_yaml.txt 547 B
- tests/test_init_and_reset.py 27 KB runs code
- tests/test_integration.py 57 KB runs code
- tests/test_ops.py 23 KB runs code
- tests/test_registers_v2.py 15 KB runs code
- tests/test_registers.py 39 KB runs code
- validate_package.py 70 KB runs code
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.
- 2d ago First seen · 125 lines · 0 tokens per session scan A 5831adea18b7
aipm-guided is a skill published in the GitHub repository miyatti777/ai-plc (49 stars, last pushed 2d ago), licensed MIT. It adds 73 tokens to every session and 9,758 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 2026-10-23.
Other skills, from other repositories
story-readiness
Checks whether a story is ready to implement: clear acceptance criteria, no open questions, valid ADR and dependencies. Use when the user asks if a story, or the sprint's stories, are ready to start or build.
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
qa-project-bootstrap
Onboard a new QA engineer to an existing codebase, or audit an existing test architecture. Produces a 30-day ramp plan: codebase orientation, framework walkthrough, test architecture audit, mentorship pairing, and first-test guidance. Use when: "QA onboarding," "new tester," "ramp up," "test architecture audit,"…
handle-linkedin-connection-request-signal
Use this skill when someone sends a team member an inbound LinkedIn connection request. An inbound request is a deliberate, ACTIVE first-party intent signal — meaningfully stronger than a passive profile view — and it deserves different scoring rules. The skill resolves and enriches the requester, gates them through…