Context Compression
guanyang/open-agent-hub
This skill should be used when long-running agent sessions need context compression, structured summarization, compaction, token-per-task optimization, or durable handoff summaries that preserve…
回答する前に、どれだけの回答深度を消費するかについてユーザーに情報に基づいた選択を提供する。ユーザーが回答の長さ、深さ、またはトークンバジェットを明示的に制御したい場合にこのスキルを使用する。トリガー条件："token budget", "token count", "token usage", "token limit", "response length", "answer depth"…
Install Token Budget Advisor
$ npx skills add affaan-m/ECC --skill token-budget-advisor -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install affaan-m/ECC token-budget-advisor --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/affaan-m/ECC.git skills-src && mkdir -p .claude/skills && cp -r skills-src/docs/ja-JP/skills/token-budget-advisor .claude/skills/token-budget-advisor && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "token-budget-advisor" agent skill from https://github.com/affaan-m/ECC/tree/main/docs/ja-JP/skills/token-budget-advisor into .claude/skills/token-budget-advisor/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "token-budget-advisor", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/affaan-m/ECC/tree/main/docs/ja-JP/skills/token-budget-advisorType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add affaan-m/ECC --skill token-budget-advisor -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install affaan-m/ECC token-budget-advisor --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/affaan-m/ECC.git skills-src && mkdir -p .agents/skills && cp -r skills-src/docs/ja-JP/skills/token-budget-advisor .agents/skills/token-budget-advisor && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "token-budget-advisor" agent skill from https://github.com/affaan-m/ECC/tree/main/docs/ja-JP/skills/token-budget-advisor into .agents/skills/token-budget-advisor/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "token-budget-advisor", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add affaan-m/ECC --skill token-budget-advisor -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install affaan-m/ECC token-budget-advisor --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/affaan-m/ECC.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/docs/ja-JP/skills/token-budget-advisor .cursor/skills/token-budget-advisor && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "token-budget-advisor" agent skill from https://github.com/affaan-m/ECC/tree/main/docs/ja-JP/skills/token-budget-advisor into .cursor/skills/token-budget-advisor/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "token-budget-advisor", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/affaan-m/ECC.git --path docs/ja-JP/skills/token-budget-advisor--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add affaan-m/ECC --skill token-budget-advisor -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install affaan-m/ECC token-budget-advisor --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/affaan-m/ECC.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/docs/ja-JP/skills/token-budget-advisor .gemini/skills/token-budget-advisor && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "token-budget-advisor" agent skill from https://github.com/affaan-m/ECC/tree/main/docs/ja-JP/skills/token-budget-advisor into .gemini/skills/token-budget-advisor/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "token-budget-advisor", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install affaan-m/ECC token-budget-advisorInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add affaan-m/ECC --skill token-budget-advisor -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/affaan-m/ECC.git skills-src && mkdir -p .github/skills && cp -r skills-src/docs/ja-JP/skills/token-budget-advisor .github/skills/token-budget-advisor && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "token-budget-advisor" agent skill from https://github.com/affaan-m/ECC/tree/main/docs/ja-JP/skills/token-budget-advisor into .github/skills/token-budget-advisor/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "token-budget-advisor", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add affaan-m/ECC --skill token-budget-advisor -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install affaan-m/ECC token-budget-advisor --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/affaan-m/ECC.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/docs/ja-JP/skills/token-budget-advisor .opencode/skills/token-budget-advisor && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "token-budget-advisor" agent skill from https://github.com/affaan-m/ECC/tree/main/docs/ja-JP/skills/token-budget-advisor into .opencode/skills/token-budget-advisor/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "token-budget-advisor", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
token-budget-advisor- GitHub stars
- 276k
- Token cost
- ~910 tokens
- SKILL.md length
- 139 words
- Files
- 1
- Skills in repo
- 683
- Repo updated
- First seen
- Licence
- MIT
At a glance
回答する前に、どれだけの回答深度を消費するかについてユーザーに情報に基づいた選択を提供する。ユーザーが回答の長さ、深さ、またはトークンバジェットを明示的に制御したい場合にこのスキルを使用する。トリガー条件："token budget", "token count", "token usage", "token limit", "response length", "answer depth"…
- Tasks that involve LLM cost and token optimization
- SKILL.md covers 使用場面, 動作原理, ショートカット——質問をスキップ and 精度について, plus 2 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Token Budget Advisor is an agent skill from affaan-m/ECC. 回答する前に、どれだけの回答深度を消費するかについてユーザーに情報に基づいた選択を提供する。ユーザーが回答の長さ、深さ、またはトークンバジェットを明示的に制御したい場合にこのスキルを使用する。トリガー条件："token budget", "token count", "token usage", "token limit", "response length", "answer depth", "short version", "brief answer", "detailed answer", "exhaustive answer", "respuesta corta vs larga", "cuántos tokens", "ahorrar tokens", "responde al 50%", "dame la versión corta", "quiero controlar cuánto…
Its SKILL.md is about 910 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in AI & LLM Engineering, covering LLM cost and token optimization. The repository describes itself as: The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond. The licence is MIT.
When your agent uses it
- Tasks that involve LLM cost and token optimization
Example prompts
- “token budget”
- “token count”
- “token usage”
- “/token-budget-advisor”
What it can do on your machine
Read from SKILL.md and the folder at commit 4eb71d9. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
Links to these hosts (documentation or services it may open):
github.com
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Token Budget Advisor loads about 910 tokens when it runs. Until then it costs about 142 tokens; SKILL.md has 139 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from affaan-m/ECC at commit 4eb71d9, republished under its MIT licence (© affaan-m). 139 words, ~910 tokens.
Download SKILL.mdSave it as
.claude/skills/token-budget-advisor/SKILL.md (or your agent's skills folder).- name
- token-budget-advisor
- description
- 回答する前に、どれだけの回答深度を消費するかについてユーザーに情報に基づいた選択を提供する。ユーザーが回答の長さ、深さ、またはトークンバジェットを明示的に制御したい場合にこのスキルを使用する。トリガー条件："token budget", "token count", "token usage", "token limit", "response length", "answer depth", "short version", "brief answer", "detailed answer", "exhaustive answer", "respuesta corta vs larga", "cuántos tokens", "ahorrar tokens", "responde al 50%", "dame la versión corta", "quiero controlar cuánto usas"、またはユーザーが回答のサイズや深さの制御を明示的に求めるその他の明確なバリエーション。トリガーしない条件：ユーザーが現在のセッションでレベルを指定済み（そのレベルを維持）、リクエストが明らかに一言の回答、または「token」が認証/セッション/支払いトークンを指している。
- origin
- community
トークンバジェットアドバイザー（TBA）
Claudeが回答する前にレスポンスフローをインターセプトし、ユーザーが回答の深さを選択できるようにする。
使用場面
- ユーザーが回答の長さや詳細度を制御したい場合
- ユーザーがトークン、バジェット、深さ、または回答の長さに言及する場合
- ユーザーが「短いバージョン」「TL;DR」「簡潔に」「25%」「詳細に」などと言う場合
- ユーザーが事前に深さ/詳細度を選択したい場合
トリガーしない場合：ユーザーが本セッションですでにレベルを設定している（静かに維持）、または回答が本質的に一行。
動作原理
ステップ 1 — 入力トークンを推定する
リポジトリの標準コンテキストバジェットのヒューリスティックスを使用して、プロンプトのトークン数を頭の中で推定する。
context-budget と同じキャリブレーションガイドラインを使用する：
- 散文：
words × 1.3 - コード集約またはコード混在/コードブロック：
chars / 4
混在コンテンツの場合、支配的なコンテンツタイプを使用し、推定ヒューリスティックスを保持する。
ステップ 2 — 複雑度に応じてレスポンスサイズを推定する
プロンプトを分類し、乗数範囲を適用して完全なレスポンスウィンドウを得る：
| 複雑度 | 乗数範囲 | プロンプト例 |
|---|---|---|
| シンプル | 3× – 8× | 「Xとは何ですか？」、はい/いいえの質問、単一の事実 |
| 中程度 | 8× – 20× | 「Xはどのように機能しますか？」 |
| 中〜高 | 10× – 25× | コンテキスト付きのコードリクエスト |
| 複雑 | 15× – 40× | マルチパート分析、比較、アーキテクチャ |
| クリエイティブ | 10× – 30× | ストーリー、散文、ナラティブライティング |
レスポンスウィンドウ = input_tokens × mult_min から input_tokens × mult_max（ただしモデルの設定済み出力トークン制限を超えない）。
ステップ 3 — 深さのオプションを提示する
回答する前に、実際に推定した数値を使用してこのブロックを提示する：
プロンプトを分析中...
入力：~[N] トークン | タイプ：[タイプ] | 複雑度：[レベル] | 言語：[言語]
深さレベルを選択してください：
[1] ベーシック (25%) -> ~[トークン数] 直接回答、前置きなし
[2] 適度 (50%) -> ~[トークン数] 回答 + 背景 + 1つの例
[3] 詳細 (75%) -> ~[トークン数] 代替案を含む完全な回答
[4] 徹底的 (100%) -> ~[トークン数] すべて、制限なし
どのレベルを選択しますか？(1-4 または「25%の深さ」「50%の深さ」「75%の深さ」「100%の深さ」)
精度：ヒューリスティック推定、約85〜90%の精度（±15%）。各レベルのトークン推定（レスポンスウィンドウ内）：
- 25% →
min + (max - min) × 0.25 - 50% →
min + (max - min) × 0.50 - 75% →
min + (max - min) × 0.75 - 100% →
max
ステップ 4 — 選択されたレベルで回答する
| レベル | 目標の長さ | 含む内容 | 省略する内容 |
|---|---|---|---|
| 25% コア | 最大2〜4文 | 直接回答、重要な結論 | コンテキスト、例、ニュアンス、代替案 |
| 50% 適度 | 1〜3段落 | 回答 + 必要なコンテキスト + 1つの例 | 深い分析、エッジケース、参考文献 |
| 75% 詳細 | 構造化された回答 | 複数の例、長所/短所、代替案 | 極端なエッジケース、網羅的な参考文献 |
| 100% 徹底的 | 制限なし | すべて——完全な分析、すべてのコード、すべての視点 | なし |
ショートカット——質問をスキップ
ユーザーがすでにレベルを示している場合、質問せずにそのレベルで即座に回答する：
| ユーザーの発言 | レベル |
|---|---|
| 「1」/「25%の深さ」/「短いバージョン」/「簡潔に」/「TL;DR」 | 25% |
| 「2」/「50%の深さ」/「適度の深さ」/「バランスの取れた回答」 | 50% |
| 「3」/「75%の深さ」/「詳細な回答」/「包括的な回答」 | 75% |
| 「4」/「100%の深さ」/「徹底的な回答」/「完全で詳細な分析」 | 100% |
ユーザーが本セッションですでにレベルを設定している場合、ユーザーが変更しない限り後続の回答も静かにそのレベルを維持する。
精度について
このスキルはヒューリスティック推定を使用する——実際のトークナイザーではない。精度は約85〜90%で偏差は±15%。常に免責事項を表示する。
例
トリガーシナリオ
- 「まず短いバージョンをください。」
- 「あなたの回答は何トークン使いますか？」
- 「50%の深さで回答してください。」
- 「徹底的な回答が欲しい、サマリーはいらない。」
- 「まず短いバージョン、次に詳細なバージョンをください。」
トリガーしないシナリオ
- 「JWTトークンとは何ですか？」
- 「チェックアウトフローは支払いトークンを使用しています。」
- 「これは正常ですか？」
- 「リファクタリングを完了してください。」
- ユーザーが本セッションの深さを選択した後の後続の質問
出典
TBA — Claude CodeのToken Budget Advisorから引用した独立スキル。 元のプロジェクトにはPython推定スクリプトも付属しているが、本リポジトリではスキルを自己完結型に保ち、ヒューリスティックスのみを使用する。
© affaan-m, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in docs/ja-JP/skills/token-budget-advisor of affaan-m/ECC.
Open the folder on GitHubat commit 4eb71d9
Compare with similar skills
Token Budget Advisor next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Token Budget Advisor this skillaffaan-m/ECC | 276k | — | ~910 | Automated safety check: Pass | MIT | |
| Context Compressionguanyang/open-agent-hub | 977 | 2 repos | ~4.6k | Automated safety check: Pass | MIT | |
| Bounty Hunter1sadjlk/bounty-hunter-skill | 282 | 1 repos | ~761 | Automated safety check: Pass | MIT | |
| Skill Shortenerluongnv89/asm | 955 | — | ~3.8k | Automated safety check: Notes | MIT | |
| Context Auditundefined-ui/second-brain-os | 1k | — | ~802 | Automated safety check: Pass | MIT | |
| Headroommomori777/Artemis | 380 | — | ~562 | Automated safety check: Pass | MIT |
Similar skills
Bounty Hunter
1sadjlk/bounty-hunter-skill
A professional AI bounty hunter persona named Atlas. An agent skill from 1sadjlk/bounty-hunter-skill.
Skill Shortener
luongnv89/asm
Refactor a too-long SKILL.md by progressive disclosure: measure token cost, classify every section KEEP/CUT/MOVE, shorten the body into references/ and scripts/, verify nothing was lost.
Context Audit
undefined-ui/second-brain-os
Audit an agent's context layout against the four places: system prompt, tools, history, tail.
Headroom
momori777/Artemis
SmartCrusher + CCR context compression — crunch large JSON arrays, tool outputs, and search results to save tokens.
AI
butterbase-ai/butterbase-skills
A skill your agent uses when calling the app's AI gateway from agent tools — chat completions, embeddings, listing models, configuring defaults or BYOK, reading token/cost usage
More from affaan-m/ECC
All 682 skills in this repoSkill Stocktake
affaan-m/ECC
Audits your installed Claude skills and commands for quality, with a quick mode for recently changed skills and a full mode that evaluates all of them through subagents.
VideoDB Video Search and Editing
affaan-m/ECC
Ingests, indexes, searches, edits and monitors video, audio and live streams through the VideoDB Python SDK, returning stream links, clips and timestamps.
Docs Governance
affaan-m/ECC
Route broad documentation-governance requests to existing ECC skills and run an opt-in, read-only audit of mapped documentation roles, links, ADR indexes, and evidence references.
Rules Distillation
affaan-m/ECC
Scans installed skills for principles that recur across them and proposes rule-file changes: append, revise, add a section, create a file or leave as covered.
Master Agreement Generator
affaan-m/ECC
Builds DRAFT counterparty agreements from one markdown template and a small JSON spec per party, with clauses picked by the party's role.
Frontend Design Direction
affaan-m/ECC
Set an ECC-specific frontend design direction for production UI work.
Related
Categories
Questions about Token Budget Advisor
What does Token Budget Advisor do?
回答する前に、どれだけの回答深度を消費するかについてユーザーに情報に基づいた選択を提供する。ユーザーが回答の長さ、深さ、またはトークンバジェットを明示的に制御したい場合にこのスキルを使用する。トリガー条件："token budget", "token count", "token usage", "token limit", "response length", "answer depth"…. Token Budget Advisor is an agent skill from affaan-m/ECC.
When should I use Token Budget Advisor?
Token Budget Advisor fits situations like: tasks that involve LLM cost and token optimization.
How do I install Token Budget Advisor in Claude Code?
Run `npx skills add affaan-m/ECC --skill token-budget-advisor -a claude-code`. Or copy the skill folder (docs/ja-JP/skills/token-budget-advisor in affaan-m/ECC) into .claude/skills/token-budget-advisor in your project. Claude Code loads it when a task matches its description.
How do I install Token Budget Advisor in Codex?
Run `npx skills add affaan-m/ECC --skill token-budget-advisor -a codex`. Or copy the skill folder (docs/ja-JP/skills/token-budget-advisor in affaan-m/ECC) into .agents/skills/token-budget-advisor in your project. Codex loads it when a task matches its description.
Can I use Token Budget Advisor in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add affaan-m/ECC --skill token-budget-advisor -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/token-budget-advisor, .gemini/skills/token-budget-advisor, .github/skills/token-budget-advisor and .opencode/skills/token-budget-advisor in your project.
What does Token Budget Advisor need to run?
SKILL.md names no scripts, command-line tools or credentials: Token Budget Advisor is instructions for the agent only.
Does Token Budget Advisor access the network?
SKILL.md names 1 domain. As links in the text: github.com. This is read from the text; nothing was executed.
Is Token Budget Advisor safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Token Budget Advisor use?
Token Budget Advisor is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Token Budget Advisor use?
About 910 tokens (SKILL.md is roughly 3.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Token Budget Advisor?
Skills that share tags, products or a category with Token Budget Advisor: Context Compression (guanyang/open-agent-hub, 977 stars), Bounty Hunter (1sadjlk/bounty-hunter-skill, 282 stars), Skill Shortener (luongnv89/asm, 955 stars) and Context Audit (undefined-ui/second-brain-os, 1k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Token Budget Advisor?
affaan-m (a GitHub user) maintains it in affaan-m/ECC, which has 276,111 GitHub stars. The repository holds 683 skills in this directory. The repository was last updated on October 10, 2026.
Source: affaan-m/ECC on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.