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/s977043/plangate/context-packagernpx skills add s977043/PlanGate --skill context-packagergit clone --depth 1 https://github.com/s977043/PlanGateWrote 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/s977043/plangate/context-packager)<a href="https://agentmods.dev/skills/s977043/plangate/context-packager"><img src="https://agentmods.dev/badge/skills/s977043/plangate/context-packager.svg" alt="Measured on agentmods" 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 | $0.00069 | $0.01417 |
| Opus 5 | $0.00034 | $0.00709 |
| Sonnet 5 | $0.00014 | $0.00283 |
| Haiku 4.5 | $0.00007 | $0.00142 |
Grade A, and why
context-packager 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 5d 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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Context Packager
タスクを AI エージェントに委譲する前に、必要最小限の文脈(Allowed Context)を構造化して出力するスキル。 「コンテキスト汚染」(不要な文脈が意思決定を歪める)を防ぐ。
目的
サブエージェントが受け取る情報を最小化することで、以下を防ぐ。
- スコープ外のファイル変更
- 無関係な仕様への解釈迷い
- 設計判断の越権(実装者が設計決定をしてしまう)
Allowed Context の 6 要素
| 要素 | 内容 | 情報源 |
|---|---|---|
| 対象ファイル(Target Files) | 変更・参照が許可されるファイルパス一覧 | plan.md の Files/Components to Touch |
| 仕様(Spec) | 受入基準・設計書・API 仕様の要点 | pbi-input.md / design.md |
| 既存テスト(Existing Tests) | 関連するテストケース・test-cases.md の参照 |
test-cases.md |
| 変更制約(Constraints) | 変更してはいけないこと、後方互換性要件 | plan.md の Constraints / Non-goals |
| 実行コマンド(Commands) | ビルド・テスト・lint コマンド | plan.md の Testing Strategy |
| 禁止スコープ(Out of Scope) | このタスクで触れてはいけない領域 | pbi-input.md の Out of scope |
手順
pbi-input.mdの受入基準・スコープ定義を読むplan.mdの Work Breakdown・変更ファイル一覧・制約を読むtest-cases.mdから関連テストケースを抽出する- 6 要素を構造化して出力形式に整形する
- Target Files 以外の情報が混入していないか最終確認する
出力形式
## Allowed Context
### Target Files
- {ファイルパス}: {変更目的}
### Spec
{受入基準・要点(箇条書き)}
### Existing Tests
- {テストファイルパス}: {テスト内容の要約}
### Constraints
- {制約 1}
- {制約 2}
### Commands
- build: {コマンド}
- test: {コマンド}
- lint: {コマンド}
### Out of Scope
- {禁止スコープ 1}
- {禁止スコープ 2}
入力
docs/working/TASK-XXXX/pbi-input.md(仕様・受入基準)docs/working/TASK-XXXX/plan.md(変更ファイル一覧・制約)docs/working/TASK-XXXX/test-cases.md(テストケース)
出力
- Allowed Context ブロック(Markdown 形式)
- サブエージェントへの委譲プロンプトに埋め込んで使用する
想定 phase
- WF-03 Solution Design(タスク分解後)
- WF-04 Build & Refine(エージェント委譲前)
カテゴリ
- context-engineering
- subagent-control
dispatch/ へのファイル保存(#581 要素3)
Allowed Context(6 要素)は委譲プロンプトに埋め込むだけでなく、docs/working/TASK-XXXX/dispatch/task-NNN-brief.md にファイルとして保存する。これにより実装者の唯一の要件ファイルとなり、会話 compaction / モデル切替後も再現可能。テンプレは docs/working/templates/dispatch/task-NNN-brief.md。
参照解決順(導入先で必ずこの順に探す): 本 Skill が参照する
docs/**は上流リポジトリ基準の相対パスであり、install.sh --claude/ plugin(Claude marketplace)/ Codex の 3 経路とも配布対象外(解決不可)。(1) 導入先リポジトリの同名パスを探す → (2) 見つからなければ 「正本<path>を参照できなかった」と明示し、本 Skill 内の記述を代替正本として扱い、推測で内容を補わない。plugin root 配下の探索はdocs/**には適用しない: plugin が配布するのはagents/commands/skills/rules等の定義ディレクトリのみでdocs/を配布対象として認識せず、plugin root 配下に相当する配布物が存在しないため、plugin root 段を置いても必ず空振りする(クラス A の rules 参照が plugin root 配下で解決できるのはrules/が実際に配布されるからであり、この非対称をdocs/**に持ち込まない)。
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.
- 5d ago First seen · 106 lines · 69 tokens per session scan A 60b31e095999
context-packager is a skill published in the GitHub repository s977043/PlanGate (2 stars, last pushed 4d ago), licensed MIT. It adds 69 tokens to every session and 1,417 once invoked, about $0.0003 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
skill-maintenance
Automated skill maintenance tool (v6 — Unified Registry + Snapshots). Full scan: [Orphan] migrate misplaced skills from category dirs OR standalone skills/<name>/ to auto-generated/, [Sync] auto-generated/ vs registry lifecycle diff (new/deleted/revived + description auto-sync via lifecycle field), [Reg]…
extract
Run the full Semantica semantic extraction pipeline on a file or selected text — NER, relations, events, coreference resolution, triplets, and validation. Clears result cache before each run. Returns Markdown tables with entity/relation/event/triplet results and inline validator warnings.
watch
File sentinel that monitors the working directory for changes and marker comments, then auto-triggers appropriate skills. Poll-based via git diff against the last scan commit. Writes intake items for batch processing and routes marker actions through /do. Use for automatic reactions to file changes; do NOT use for…
review
5-pass structured code review — correctness, security, performance, readability, consistency.
live-preview
Mid-build visual verification loop. Takes screenshots of components during construction, not just after. Catches visual regressions and invisible features before they compound. Requires Playwright or similar screenshot tool.
marshal
Meta-orchestrator that takes any direction — broad, specific, or vague — and autonomously chains skills and context into actionable work. Gathers context from codebase, docs, and memory. Only asks the user when it genuinely cannot proceed. Single-session orchestrator.