tokf
mpecan/tokf
tokf is a command-line utility that intercepts and filters verbose CLI outputs using TOML rules, reducing LLM context consumption by 60% to 90%.
192 19MITUpdated 2026-08-12
79
GreatOverview
Designed specifically for AI coding agents and developers, tokf wraps common development commands like `git push`, `cargo test`, and `docker build` to strip away progress bars, compilation noise, and boilerplate text. By presenting a clean, concise signal to language models, it dramatically reduces token waste and preserves context windows. It supports custom filter definitions, automatic shell/tool hooks, and session discovery to audit token savings over time.
Capabilities
- ▸Intercept and filter CLI command outputs using TOML rules
- ▸Scan past AI coding sessions for unoptimized commands via tokf discover
- ▸Automatically integrate with AI tools like Claude Code, Codex, and OpenCode via shell hooks
- ▸Support custom filter ejection, testing, and safety verification
- ▸Preserve ANSI colors when requested while maintaining internal pattern matching
Best for
Reducing token consumption for AI coding agents running repetitive CLI commands, Cleaning up verbose test runner outputs like cargo test or pytest, Auditing past coding sessions to identify missed token optimization opportunities, Writing and verifying custom TOML-based command output filters
Works with
Claude CodeCodexOpenCode
Evoa Score breakdown= Σ (score × weight)
79Task usefulness20%88 → +17.6
実タスクにどれだけ役立つか（機能の豊富さ・用途の明確さ）。 — AIによるcapabilities/use-cases解析
Code quality15%90 → +13.5
実装・指示の品質。 — AIによるSKILL.md/README解析
Maintenance15%100 → +15.0
リポジトリがどれだけ活発に保守されているか。 — GitHub 最終push日時の新しさ
Documentation12%35 → +4.2
ドキュメントの充実度・分かりやすさ。 — README/独自要約の情報量
Security15%80 → +12.0
危険・不審な挙動が無いか。 — AIによるセキュリティレビュー
Originality10%85 → +8.5
ありふれたラッパーではない独自性。 — AIによる独自性判定
Popularity8%59 → +4.7
コミュニティの採用度。 — GitHub Stars/Forks（対数スケール）
Compatibility5%75 → +3.8
対応AIエージェントの広さ。 — AIによる対応エージェント判定
Weighted total79.3 / 100
ライセンス不明/制限あり（Red）のSkillは総合スコアに0.85倍の補正を適用します。 ランキングはこのScoreのみで決まり、広告で変わりません。 算出方法の詳細 →
Security considerations
Executes local CLI commands and wraps child processes; includes built-in safety check suites for filter scripts to guard against prompt and shell injection.
Categories
Summary and analysis are original content generated by AI Skills Rank. The skill's source text is not reproduced here — view it on the linked repository.