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/working-contextnpx skills add s977043/PlanGate --skill working-contextgit 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/working-context)<a href="https://agentmods.dev/skills/s977043/plangate/working-context"><img src="https://agentmods.dev/badge/skills/s977043/plangate/working-context.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 | $0.00056 | $0.02778 |
| Opus 5 | $0.00028 | $0.01389 |
| Sonnet 5 | $0.00011 | $0.00556 |
| Haiku 4.5 | $0.00006 | $0.00278 |
Grade A, and why
working-context scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Working Context (PlanGate / Codex 共用)
PlanGate の docs/working/TASK-XXXX/ 配下を L0〜L3 の Progressive Disclosure プロトコル で読み込み、更新する skill。プロトコル詳細は .claude/rules/working-context.md を正本とする（導入先での解決手順は下記「参照解決順」）。
Read First (L0 / 常に読む)
参照解決順（導入先で必ずこの順に探す）
本 skill の参照は上流リポジトリ（s977043/plangate）基準の相対パスで書かれている。
本 skill は正本を再掲せず参照するため、正本が引けないと「正本に基づく運用」はできない
（その場合は手順 3 の代替プロトコルに落とし、正本未参照であることを明示する）。次の順で探索する:
- 導入先リポジトリの相対パス（
.claude/rules/working-context.md） - 無ければ plugin root 配下（
<plugin_root>/rules/working-context.md）<plugin_root>は Bash でls "${CLAUDE_PLUGIN_ROOT}/rules/"を実行して得た絶対パス。 Read ツールは絶対パスを要求し環境変数を展開しないため、${CLAUDE_PLUGIN_ROOT}/...という文字列をそのまま Read しても必ず失敗する- 変数が空・未設定なら glob（
~/.claude/plugins/cache/**等）で推測せず 3 へ進む
- どちらにも無い場合は 「解決できなかった」と明示し、推測で内容を補わない。
L0〜L3 の段取り・出力先は本 skill 本文で代替し、正本未参照である旨を
status.mdに記録する
plugin root 配下の探索は docs/** には適用しない（手順 2 は rules/*.md 等の
配布対象にのみ適用する）: 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/（本 skill が参照する docs/working/templates/*.md を含む）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必ず空振りする。
docs/** は手順 1 で解決できなければ手順 2 を飛ばして手順 3 へ進む。
手順 3 に落ちても判定基準は緩めない: 正本が引けない場合の代替は「L0=
INDEX.md→current-state.md、L1=フェーズ該当ファイル、L2=evidence//decision-log.jsonl、 L3=status.md全体」の段取りと本 skill「Rules」節（YYYY-MM-DD HH:mm必須・handoff 6 要素 必須・逸脱記録）であって、省略ではない。正本を参照できないことを理由に判定基準・ ゲートを緩めてはならない。
| 参照 | install.sh --claude 経由 |
plugin（Claude marketplace）経由 | Codex 経由 |
|---|---|---|---|
rules/*.md（下記 3） |
.claude/rules/ に着地（解決可） |
<plugin_root>/rules/ で解決 |
未配置（解決不可 → 手順 3 へ） |
docs/working/templates/*.md |
コピー対象外（解決不可） | バンドル対象外（解決不可） | 未配置（解決不可） |
bin/**（CLI） |
コピー対象外（解決不可） | バンドル対象外（解決不可） | 未配置（解決不可） |
scripts/** |
コピー対象外（解決不可） | <plugin_root>/scripts/ は存在するが install-plangate-skills.sh のみ（context-engine.py 等は解決不可） |
未配置（解決不可） |
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.
- 4d ago First seen · 110 lines · 56 tokens per session scan A 28dac2807242
working-context is a skill published in the GitHub repository s977043/PlanGate (2 stars, last pushed 4d ago), licensed MIT. It adds 56 tokens to every session and 2,778 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
decision
Full decision lifecycle in Semantica � record, query, find precedents (hybrid/advanced), analyze influence, explain, insights dashboard, list, and record exceptions. Uses AgentContext, ContextGraph, DecisionQuery, CausalChainAnalyzer, DecisionRecorder.
session-handoff
Synthesizes the current session into a structured HANDOFF block for context transfer between sessions. Captures what was built, decisions made, and unresolved items.
aidd-context:02:project-init
Initialize or refresh the project memory bank, scaffold the rules directory, and ensure AI context files contain the project memory block. Use when running aidd init for the first time, bootstrapping a new project, or re-running the init flow on an existing project. Do NOT use for updating individual memory files…
02-project-memory
Build the project's memory of its architecture, conventions, and decisions, and wire it into your AI tools. Use when the user wants to set up or refresh project memory, or rewire it into a tool. Not for editing one existing memory file.
10-learn
Capture durable project learnings. Use when the user wants to remember, record, or formalize a decision, convention, lesson, pitfall, reusable workflow, or review finding. Not for preferences or temporary notes.
aidd-context:05:learn
Capture and store learnings from recently implemented features into memory bank, decisions, or coding rules.