# Add to your Claude Code skills
git clone https://github.com/mpecan/tokf
README.md
tokf
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. tokf intercepts that output, applies a TOML filter, and emits only what matters — so your AI agent sees a clean signal instead of hundreds of wasted tokens.
Before / After
cargo test — 61 lines → 1 line:
Compiling tokf v0.2.0 (/home/user/tokf)
Compiling proc-macro2 v1.0.92
Compiling unicode-ident v1.0.14
Compiling quote v1.0.38
Compiling syn v2.0.96
Compiling serde_derive v1.0.217
Compiling serde v1.0.217
...
running 47 tests
test config::tests::test_load ... ok
test filter::tests::test_skip ... ok
test filter::tests::test_keep ... ok
test filter::tests::test_extract ... ok
...
test result: ok. 47 passed; 0 failed; 0 ignored
finished in 2.31s
✓ 47 passed (2.31s)
git push — 8 lines → 1 line:
Enumerating objects: 5, done.
Counting objects: 100% (5/5), done.
Delta compression using up to 10 threads
Compressing objects: 100% (3/3), done.
Writing objects: 100% (3/3), 312 bytes | 312.00 KiB/s, done.
Total 3 (delta 2), reused 0 (delta 0), pack-reused 0
remote: Resolving deltas: 100% (2/2), completed with 2 local objects.
To github.com:user/repo.git
a1b2c3d..e4f5a6b main -> main
brew install mpecan/tokf/tokf # or: cargo install tokf
tokf setup # detect your AI tools and install hooks
That's it. Every command your AI agent runs is now automatically filtered.
Run tokf gain to see how many tokens you've saved, or tokf setup --refresh to re-run detection.
Installation
Homebrew (macOS and Linux)
brew install mpecan/tokf/tokf
cargo
cargo install tokf
Build from source
git clone https://github.com/mpecan/tokf
cd tokf
cargo build --release
# binary at target/release/tokf
How it works
tokf run git push origin main
tokf looks up a filter for git push, runs the command, and applies the filter. The filter logic lives in plain TOML files — no recompilation required. Anyone can author, share, or override a filter.
Set up automatic filtering
If you use an AI coding tool, install the hook so every command is filtered automatically — no tokf run prefix needed:
# Claude Code (recommended: --global so it works in every project)
tokf hook install --global
# OpenCode
tokf hook install --tool opencode --global
# OpenAI Codex CLI
tokf hook install --tool codex --global
Drop --global to install for the current project only. See Claude Code hook for details on each tool, the --path flag, and optional extras like the filter-authoring skill.
Usage
Run a command with filtering
tokf run git push origin main
tokf run cargo test
tokf run docker build .
tokf verify # run all test suites
tokf verify git/push # run a specific suite
tokf verify --list # list available suites and case counts
tokf verify --json # output results as JSON
tokf verify --require-all # fail if any filter has no test suite
tokf verify --list --require-all # show coverage per filter
tokf verify --scope project # only project-local filters (.tokf/filters/)
tokf verify --scope global # only user-level filters (~/.config/tokf/filters/)
tokf verify --scope stdlib # only built-in stdlib (filters/ in CWD)
tokf verify --safety # run safety checks (prompt injection, shell injection, hidden unicode)
tokf verify git/push --safety # safety check a specific filter
Task runner filtering
tokf automatically wraps make and just so that each recipe line is individually filtered:
make check # each recipe line (cargo test, cargo clippy, ...) is filtered
just test # same — each recipe runs through tokf
tokf ls # list all filters
tokf which "cargo test" # which filter would match
tokf show git/push # print the TOML source
Customize a built-in filter
tokf eject cargo/build # copy to .tokf/filters/ (project-local)
tokf eject cargo/build --global # copy to ~/.config/tokf/filters/ (user-level)
This copies the filter TOML and its test suite to your config directory, where it shadows the built-in. Edit the ejected copy freely — tokf's priority system ensures your version is used instead of the original.
Flags
| Flag | Description |
|---|---|
| --timing | Print how long filtering took |
| --verbose | Show which filter was matched (also explains skipped rewrites) |
| --no-filter | Pass output through without filtering |
| --no-cache | Bypass the filter discovery cache |
| --no-mask-exit-code | Disable exit-code masking. By default tokf exits 0 and prepends Error: Exit code N on failure |
| --preserve-color | Preserve ANSI color codes in filtered output (env: TOKF_PRESERVE_COLOR=1). See Color passthrough below |
| --baseline-pipe | Pipe command for fair baseline accounting (injected by rewrite) |
| --prefer-less | Compare filtered vs piped output and use whichever is smaller (requires --baseline-pipe) |
Color passthrough
By default, filters with strip_ansi = true permanently remove ANSI escape codes. The --preserve-color flag changes this: tokf strips ANSI internally for pattern matching (skip, keep, dedup) but restores the original colored lines in the final output. When --preserve-color is active it overrides strip_ansi = true in the filter config.
tokf does not force commands to emit color — you must ensure the child command outputs ANSI codes (e.g. via FORCE_COLOR=1 or --color=always):
# Node.js / Vitest / Jest
FORCE_COLOR=1 tokf run --preserve-color npm test
# Cargo
tokf run --preserve-color cargo test -- --color=always
# Or set the env var once for all invocations
export TOKF_PRESERVE_COLOR=1
FORCE_COLOR=1 tokf run npm test
Limitations: color passthrough applies to the skip/keep/dedup pipeline (stages 2–2.5). The match_output, parse, and lua_script stages operate on clean text and are unaffected by this flag. [[replace]] rules run on the raw text before the color split, so when --preserve-color is enabled their patterns may need to account for ANSI escape codes, similar to branch-level skip patterns, which also match against the restored colored text.
Built-in filter library
| Filter | Command |
|---|---|
| git/add | git add |
| git/commit | git commit |
| git/diff | git diff — overrides to git diff --stat for compact output. Pass -p/--patch/--no-stat/-U<n>/--name-only/--name-status/--numstat/--shortstat/--raw to skip the override and get the requested format instead |
| git/log | git log — overrides to git log --oneline --no-decorate -n 20. Pass -p/--patch/--format/--pretty/--graph/--stat/--shortstat/--dirstat/--name-only/--name-status/-L to skip the override. Empty results emit a one-line hint pointing at common causes (untracked pathspec, missing --all, missing --follow) instead of nothing — this stops agents looping through flag variations trying to escape a non-existent filter |
| git/push | git push |
| git/show | git show |
| git/status | git status — runs git status --porcelain=v1 -b -uall --find-renames; shows branch + upstream sync state ([synced], [ahead N], [behind N], (no upstream)) and one porcelain line per changed file (M src/main.rs, ?? scratch.rs, R old.rs -> new.rs). -uall lists every untracked file individually instead of collapsing newly-created directories. When 3+ files share a directory prefix the listing is restructured into a directory tree (see [tree]), writing each shared prefix once. Measured 24.4% averaged token reduction across the bundled test fixtures |
| cargo/build | cargo build |
| cargo/check | cargo check |
| cargo/clippy | cargo clippy |
| cargo/fmt | cargo fmt |
| cargo/install | cargo install * |
| cargo/test | cargo test |
| docker/* | docker build, docker compose, docker images, docker ps |
| npm/run | npm run * |
| npm/test | npm test, pnpm test, yarn test (with vitest/jest variants) |
| pnpm/* | pnpm add, pnpm install |
| go/* | go build, go vet |
| gradle/* | gradle build, gradle test, gradle dependencies |
| gh/* | gh pr list, gh pr view, gh pr checks, gh issue list, gh issue view |
| kubectl/* | kubectl get pods |
| next/* | next build |
| prisma/* | prisma generate |
| pytest | Python test runner |
| tsc | TypeScript compiler |
| ls | ls |
Generic Commands
When no dedicated filter exists for a command, three built-in subcommands provide useful compression for ar
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
A Claude Code plugin that automatically captures everything Claude does during your coding sessions, compresses it with AI (using Claude's agent-sdk), and injects relevant context back into future sessions.
