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.
Interpret all RTK rewrite exit codes and respond appropriately:
- Exit 0 (Allow): auto-apply rewrite
- Exit 1 (Passthrough): no RTK equivalent, pass through unchanged
- Exit 2 (Deny): block the call entirely
- Exit 3 (Ask): rewrite available, require user approval via
requireApproval with allow-once/deny decisions
Uses execFileSync (not execSync) to avoid shell injection. Returns
a [string | null, RewriteVerdict?] tuple from tryRewrite so the
before_tool_call hook can react to each verdict type.
"allow-always" omitted from allowedDecisions because OpenClaw does
not auto-persist approval for plugin hooks — see:
https://docs.openclaw.ai/plugins/plugin-permission-requests#troubleshootingCloses#2202
* feat: add OpenClaw plugin for transparent exec rewriting
Adds an OpenClaw plugin that intercepts exec tool calls via the
before_tool_call hook and rewrites commands to their RTK equivalents.
This is the OpenClaw equivalent of hooks/rtk-rewrite.sh for Claude Code.
The plugin:
- Registers a before_tool_call hook on the exec tool
- Rewrites git, grep, find, ls, gh, docker, kubectl, and test commands
- Guards against rewriting piped/compound commands and heredocs
- Returns properly typed PluginHookBeforeToolCallResult
- Supports enabled/verbose config options
Measured savings: 48-87% token reduction on common commands.
Files:
- openclaw/index.ts — plugin source
- openclaw/openclaw.plugin.json — plugin manifest
- openclaw/README.md — installation and usage docs
* refactor: delegate OpenClaw plugin to rtk rewrite
Replace 60+ hardcoded regex rules with a single call to `rtk rewrite`,
matching the OpenCode plugin pattern (hooks/opencode-rtk.ts).
Benefits:
- Zero maintenance: new RTK filters work automatically
- Single source of truth: rewrite logic in Rust (src/discover/registry.rs)
- 122 → 73 lines, no rule duplication
Also: rebase on develop, fix homepage URL, bump version to 1.0.0.
Signed-off-by: Patrick szymkowiak <patrick.szymkowiak@innovtech.eu>
* feat: add package.json for npm publishing
Enables `openclaw plugins install @rtk-ai/rtk-rewrite` for OpenClaw users.
Signed-off-by: Patrick szymkowiak <patrick.szymkowiak@innovtech.eu>
---------
Signed-off-by: Patrick szymkowiak <patrick.szymkowiak@innovtech.eu>
Co-authored-by: Patrick szymkowiak <patrick.szymkowiak@innovtech.eu>
Adrien Eppling