RTK was documented as delivering "60-90% token savings", which reads as a
cost reduction. What RTK actually reduces is bash output bytes. Those are
one contributor to input tokens, which are themselves only part of a bill
that also counts output tokens, so the reduction dilutes at every step.
- add docs/guide/resources/savings-explained.md as the canonical explainer:
the savings chain, both estimators, and what RTK does not reduce
- rescope the headline claim across README (7 languages), the guide, hook
rules, agent definitions and module READMEs
- relabel per-command tables as bash output reduction, keeping every figure
- document that reported tokens are estimates: rtk gain uses bytes/4
(src/core/tracking.rs), filter tests use split_whitespace().count().
Neither is a real tokenizer, so ratios hold but absolute counts do not
Remove figures that had no source: the $3/Mtok constant and its $36
example, the +/-10% tokenization accuracy claim, the 99.5% hook-install
figure, the invented session tables in README and INSTALL, and the 30-50%
parser range.
CHANGELOG is untouched. Shipped release notes stay as a historical record.
Commands and ecosystems automatically optimized by RTK, with typical bash output reduction
order
1
What RTK Optimizes
Once RTK is installed with a hook, these commands are automatically intercepted and filtered. You run them normally — the hook rewrites them transparently before execution.
Typical bash output reduction: 60-99%.
:::note
Every percentage below measures bash output bytes removed — the only thing RTK controls. Those bytes are one contributor to input tokens, and input tokens are only part of a bill that also counts output tokens. See How RTK Savings Work before reading these numbers as cost figures.
:::
Git
Command
Bash output reduction
What changes
git status
75-93%
Compact stat format, grouped by state
git log
80-92%
Hash + author + subject only
git diff
70%
Context reduced, headers stripped
git show
70%
Same as diff
git stash list
75%
Compact one-line per entry
GitHub CLI
Command
Bash output reduction
What changes
gh pr view
87%
Removes ASCII art and verbose metadata
gh pr checks
79%
Status + name only, failures highlighted
gh run list
82%
Compact workflow run summary
gh issue view
80%
Body only, no decoration
Graphite (Stacked PRs)
Command
Bash output reduction
What changes
gt log
75%
Stack summary only
gt status
70%
Current branch context
Cargo / Rust
Command
Bash output reduction
What changes
cargo test
90%
Failures only, passed tests suppressed
cargo nextest
90%
Same as test
cargo build
80%
Errors and warnings only
cargo check
80%
Errors and warnings only
cargo clippy
80%
Lint warnings grouped by file
JavaScript / TypeScript
Command
Bash output reduction
What changes
jest
94-99%
Failures only
vitest
94-99%
Failures only
tsc
75%
Type errors grouped by file
eslint
84%
Violations grouped by rule
pnpm list
70-90%
Compact dependency tree
pnpm outdated
70%
Package + current + latest only
next build
80%
Route summary + errors only
prisma migrate
75%
Migration status only
playwright test
90%
Failures + trace links only
Python
Command
Bash output reduction
What changes
pytest
80-90%
Failures only
ruff check
75%
Violations grouped by file
mypy
75%
Type errors grouped by file
pip install
70%
Installed packages only, progress stripped
Go
Command
Bash output reduction
What changes
go test
80-90%
Failures only
golangci-lint run
75%
Violations grouped by file
go build
75%
Errors only
Ruby
Command
Bash output reduction
What changes
rspec
80-90%
Failures only
rubocop
75%
Offenses grouped by file
rake
70%
Task output, build errors highlighted
.NET
Command
Bash output reduction
What changes
dotnet build
80%
Errors and warnings only
dotnet test
85-90%
Failures only
dotnet format
75%
Changed files only
Docker / Kubernetes
Command
Bash output reduction
What changes
docker ps
65%
Essential columns (name, image, status, port)
docker images
60%
Name + tag + size only
docker logs
70%
Deduplicated, last N lines
docker compose up
75%
Service status, errors highlighted
kubectl get pods
65%
Name + status + restarts only
kubectl logs
70%
Deduplicated entries
Files and Search
Command
Bash output reduction
What changes
ls
80%
Tree format with file counts
find
75%
Tree format
grep
70%
Truncated lines, grouped by file
diff
65%
Context reduced
wc
60%
Compact counts
cat / head / tail <file>
60-80%
Smart file reading via rtk read
rtk smart <file>
85%
2-line heuristic code summary (signatures only)
Cloud and Data
Command
Bash output reduction
What changes
aws
70%
JSON condensed, relevant fields only
psql
65%
Query results without decoration
curl
60%
Response body only, headers stripped
Global flags
These flags apply to all RTK commands and can push the bash output reduction even higher:
Flag
Description
--ultra-compact
ASCII icons, inline format — extra token reduction on top of normal filtering
-v / --verbose
Show filtering details on stderr (-v, -vv, -vvv for increasing detail)
# Ultra-compact: even smaller output
rtk git log --ultra-compact
# Debug: see what RTK is doing
rtk git status -vvv
:::note
Use --ultra-compact (long form) rather than -u when working with Git commands. Git's own -u flag means --set-upstream and the short form can cause confusion.
:::
Commands that are not rewritten
If a command isn't in the list above, RTK runs it through passthrough — the output reaches the LLM unchanged. You can explicitly track unsupported commands:
rtk proxy make install # runs make install, tracks usage, no filtering
To check which commands were missed opportunities: rtk discover.
Adrien Eppling
a1673f7428