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 agentmods add skills/thkt/dotclaude/previewnpx skills add thkt/dotclaude --skill previewgit clone --depth 1 https://github.com/thkt/dotclaudeWhat 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 | $0.00041 | $0.00753 |
| Opus 5 | $0.00020 | $0.00377 |
| Sonnet 5 | $0.00008 | $0.00151 |
| Haiku 4.5 | $0.00004 | $0.00075 |
Grade A, and why
preview 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.
What it actually says
/preview - Plan 整合性の確認
入力
$ARGUMENTS は PR の URL、番号、または空。空なら現在ブランチから検出する。
実行
gh pr view $ARGUMENTS --json number,title,body,files,urlで PR を識別する。失敗したら$ARGUMENTSなしで再実行する- PR が無い、または作業ツリーが dirty なら中止する。判定は
git status --porcelain - 意図のソースを特定する (§ 意図のソース)
gh pr diff $PRを読み、§ チェックの各項目を判定する- § 出力形式で結果を出す
意図のソース
上から順に探し、最初に見つかったものを使う。
- 起点の issue の
## Plan節。ブランチ名や commit message の issue 参照からgh issue view <N>で取る .claude/workspace/planning/の*.plan.md。ブランチ名か PR タイトルに一致するもの- PR 説明と commit message。ここまで落ちたときは U-NNN と T-NNN の行を飛ばし、Scope creep と Impl-wrong だけを見る
チェック
各フラグには根拠となる plan の行を引用する。引用の無い missing と wrong は根拠が無いので落とす。
| チェック | ソース | 条件 | フラグ |
|---|---|---|---|
| Unit coverage | ## Plan 節の U-NNN unit |
plan あり | missing |
| Test coverage | ## Plan 節の T-NNN 受け入れテスト |
plan あり | missing |
| Scope creep | diff vs 意図のソース | 常時 | out-of-scope |
| Impl-wrong | diff の振る舞い vs unit goal / T-NNN | 常時 | wrong |
出力形式
会話に出す。ファイルには保存せず、PR にも投稿しない。
Plan Alignment: [CLEAN | MISSING <N> | OUT-OF-SCOPE <N> | WRONG <N> | MIXED]
Intent source: <issue #N Plan section | *.plan.md path | PR description | commit messages>
Missing (U): U-NNN - <description> (plan: "<quoted line>")
Missing (T): T-NNN - <description> (plan: "<quoted line>")
Out-of-scope: <file or area> - not traceable to stated intent
Wrong: <U-NNN/T-NNN> - implemented but <gap> (plan: "<quoted line>")
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 · 55 lines · 41 tokens per session scan A a8c99ca1ce85
preview is a skill published in the GitHub repository thkt/dotclaude (11 stars, last pushed 2d ago), licensed MIT. It adds 41 tokens to every session and 753 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
create-modal
Create declarative modals using the modal library API. Covers modal types (confirm, input, select, form), sections (Text, Buttons, Input, Textarea, Checkbox, List, Combo, When, Custom), rendering with OverlayModal, and keyboard/mouse handling. Use when adding modals or dialogs to the application.
create-plugin
Create new sidecar plugins implementing the plugin.Plugin interface, rendering views with Bubble Tea, handling keyboard input via keymap contexts, and integrating with the app shell (footer hints, event bus, adapters). Use when creating a new plugin, modifying plugin architecture, or debugging plugin…
merge-strategy
Git merge strategies, conflict resolution approaches, merge vs rebase recommendations, and branch integration patterns in sidecar. Covers pull strategy menu, direct merge workflow, squash merge, commit message templates, configurable defaults, and protected branches. Use when working on git merge features or making…
autoprompt
Explicit-only useful-first orchestration. Invoke /autoprompt to turn a mission into one executable roadmap, build dependency-safe lanes, and verify the result with independent reviewers. Never infer invocation from ordinary requests. Never resume from leftover artifacts without an explicit resume instruction.
autoprompt
Explicit-only useful-first orchestration. Invoke /autoprompt to turn a mission into one executable roadmap, build dependency-safe lanes, and verify the result with independent reviewers. Never infer invocation from ordinary requests. Never resume from leftover artifacts without an explicit resume instruction.
autoprompt
Explicit-only useful-first orchestration. Invoke /autoprompt to turn a mission into one executable roadmap, build dependency-safe lanes, and verify the result with independent reviewers. Never infer invocation from ordinary requests. Never resume from leftover artifacts without an explicit resume instruction.