/codex-discover
Find missed token savings by scanning AI coding session files for commands that ran without tokf filtering.
$ npx -y skills add mpecan/tokf --skill codex-discover --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
- You can call itInvoke it directly when you want it.
- Slash command
/codex-discover
Context preview
The summary Claude sees to decide when to auto-load this skill.
Find missed token savings by scanning AI coding session files for commands that ran without tokf filtering.
SKILL.md
codex-discover.SKILL.mdname: tokf-discover description: Find missed token savings by scanning AI coding session files for commands that ran without tokf filtering.
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 (also `24h`, `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
1. Run `tokf discover` to identify top savings opportunities 2. For commands with existing filters: run `tokf hook install --tool codex` to set up automatic filtering 3. For commands without filters: create a custom filter with `tokf eject` 4. Re-run `tokf discover` after changes to verify improvement
JSON Output
Use `--json` for integration with other tools:
tokf discover --json
tokf.net — reduce LLM context consumption from CLI commands by 60–90%. Commands like git push, cargo test, and docker build produce verbose output packed with progress bars, compile noise, and boilerplate.
Repo: mpecan/tokf
Other skills on tokf.
- /codex-run
Compress verbose CLI output with tokf before returning results. Activates for git, cargo, npm, docker, go, gradle, kubectl, and other supported commands.
Open skill - /tokf-discover
Find missed token savings in Claude Code sessions and create filters for unfiltered commands
Open skill - /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.
Open skill