ReddRadar
Agent skill
tokf-discover
Find missed token savings by scanning AI coding session files for commands that ran without tokf filtering.
Install this agent skill to your Project
npx add-skill https://github.com/mpecan/tokf/tree/main/crates/tokf-cli/skills/codex-discover
SKILL.md
tokf discover — Find Missed Token Savings
Use this skill to analyze past sessions and find commands that are running without tokf filtering, wasting tokens on verbose output.
Quick Start
Run tokf discover in the project directory to scan recent sessions:
tokf discover
Options
--all— scan all projects, not just the current one--since 7d— only scan sessions from the last 7 days (also24h,30m)--limit 0— show all results (default: top 20)--json— output as JSON for programmatic use--session <path>— scan a specific session file--project <path>— scan sessions for a specific project path
Workflow
- Run
tokf discoverto identify top savings opportunities - For commands with existing filters: run
tokf hook install --tool codexto set up automatic filtering - For commands without filters: create a custom filter with
tokf eject - Re-run
tokf discoverafter changes to verify improvement
JSON Output
Use --json for integration with other tools:
tokf discover --json
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
mpecan/tokf
tokf-filter
This skill should be used when the user asks to "create a filter", "write a tokf filter", "add a filter for <tool>", "how do I filter output", or needs guidance on tokf filter step types, templates, pipes, or placement conventions.
mpecan/tokf
tokf-discover
Find missed token savings in Claude Code sessions and create filters for unfiltered commands
mpecan/tokf
tokf-run
Compress verbose CLI output with tokf before returning results. Activates for git, cargo, npm, docker, go, gradle, kubectl, and other supported commands.
davila7/claude-code-templates
verl-rl-training
Provides guidance for training LLMs with reinforcement learning using verl (Volcano Engine RL). Use when implementing RLHF, GRPO, PPO, or other RL algorithms for LLM post-training at scale with flexible infrastructure backends.
davila7/claude-code-templates
openrlhf-training
High-performance RLHF framework with Ray+vLLM acceleration. Use for PPO, GRPO, RLOO, DPO training of large models (7B-70B+). Built on Ray, vLLM, ZeRO-3. 2× faster than DeepSpeedChat with distributed architecture and GPU resource sharing.
davila7/claude-code-templates
gguf-quantization
GGUF format and llama.cpp quantization for efficient CPU/GPU inference. Use when deploying models on consumer hardware, Apple Silicon, or when needing flexible quantization from 2-8 bit without GPU requirements.
Didn't find tool you were looking for?