snip
CLI proxy that reduces LLM token usage by 60-90%. Declarative YAML filters for Claude Code, Cursor, Copilot, Gemini. rtk alternative in Go.
Runssource: GitHubhomepageGoMITcommit af3471fd3891
Go, MIT licensed. The project labels itself: ai coding, ai tools, aider, claude code, cli, cline, codex and context window.
snip runs. An Argusic agent installed it in 2.1 minutes and hit no errors on a clean machine with no GPU, and the whole session was recorded.
snip builds as a static binary, all unit and race tests pass, all 55 inline filter YAML tests pass, and the binary's help/version/run/gain/config commands all produce correct output
What the agent ended up with on a clean machine, in its own words. How this is measured
Measured by Argusic on a fresh machine every time. Every number links to its evidence. Argusic Score 100 of 100 (the mean of this project's run scores).
At a glance
Subject data from GitHub, linked at the top of this page, refreshed . Test data by Argusic (CC BY 4.0); every number links to a run page with the full log, the recording, and their sha256 hashes.
What was measured
From the run that decided this verdict. Every line is a recorded value, not an estimate.
- Install time
- 2 minutes
- Cold machine to finish
- 2 minutes
- Errors hit and fixed
- 0 hit, 0 fixed with no human help
- How the result was proved
- go test -cover ./... passed all 18 packages; go test -race -cover ./... passed all 18 packages; go run ./cmd/snip verify passed 55/55 filter tests; ./snip --help, --version, run, gain, config all produced correct output
- Model tokens used
- 28,078
- Exact commit tested
- af3471fd3891
- Container image
- sha256:cdd920bce783
What was not measured
The other half, so you can see exactly how far this evidence goes. A gap is printed as a gap and never filled in.
- Peak GPU memory
- this ran on a CPU machine, so there was no GPU to sample
- Behaviour over a long run
- each attempt uses the smallest documented settings and a fixed time budget, so this measures whether it runs, not how it holds up under load
The end of the recording
The last lines of the terminal session that decided this verdict, exactly as they were recorded.
Avg savings 50.6% Efficiency Good Total time 0.0s ██████████░░░░░░░░░░ 51% Top commands by tokens saved Command Runs Saved Savings Impact ─────── ──── ───── ─────── ──────────── ls -la 1 238 50.6% ████████████ All good — the project builds, all 18 packages pass tests (including race detection), all 55 filter… tokens used 28,078 All good — the project builds, all 18 packages pass tests (including race detection), all 55 filter…
Replay the whole session, every command from a clean machine to this point.
How it was tested
One agent, one container, no human help. It installs the project the way its own documentation says to, runs it, and fixes what breaks. Everything below is recorded as it happened: the terminal session, the log and the exact commit. The full method.
Strengths and limits
Measured facts, not opinions. How this is written.
What went well
- Reached a running state on a clean machine, with the session recorded.
- Installed in 2.1 minutes, faster than the median of the 6 comparable projects Argusic has measured.
- Nothing broke on the way: zero errors between clone and running.
- Ran without a GPU, so it does not need one to start.
- Licensed MIT, as reported by its host.
What did not, or is not known
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
Of the 7 ai-coding projects Argusic has installed and timed, snip was the 3rd fastest to reach a running state, and 6 of 7 reached one at all.
What it is a reasonable choice for
- Trying it on a laptop or a small server: it reached a running state without a GPU.
- A quick evaluation: it was running 2.1 minutes after the clone.
- Following its own README: the documented path worked with nothing to fix.
Also tested, in the same area
Every one of these was installed and run by Argusic on a clean machine. Nothing appears here that was not tested.
Run history
Topics (from GitHub)
ai-codingai-toolsaiderclaude-codecliclinecodexcontext-windowcopilotcursordeveloper-toolsfiltergeminigolangllmrtk-alternativetoken-optimizationtoken-reductionwindsurfyaml
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/snip)Questions
- Does snip run?
- Yes. snip runs. Argusic installed and launched it on a clean machine in 2 minutes, hitting 0 errors on the way, and recorded the session.
- How did Argusic test snip?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit af3471fd3891. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test snip?
- The run that produced this verdict cost $0.02: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does snip take to install?
- 2.1 minutes in the run that decided this verdict, from a clean machine to a running state. That is one measured attempt, not an average.
- Does snip need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing snip?
- Nothing did, in the recorded run: zero errors between clone and running.
- How does snip compare with the alternatives?
- Of the 7 ai-coding projects Argusic has installed and timed, snip was the 3rd fastest to reach a running state, and 6 of 7 reached one at all.
- Where is the evidence for snip?
- The recorded run is on this page, each linking to its full log and terminal recording, stored with a sha256 fingerprint so it cannot be quietly altered.