Skip to content
Open
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
12 changes: 12 additions & 0 deletions hooks/antigravity/rules.md
Original file line number Diff line number Diff line change
Expand Up @@ -30,3 +30,15 @@ rtk proxy <cmd> # Run raw (no filtering, for debugging)
## Why

RTK filters and compresses command output before it reaches the LLM context, saving 60-90% tokens on common operations. Always use `rtk <cmd>` instead of raw commands.

## Reading the full output

RTK output is a filtered summary — for most commands it keeps what matters
(test failures, panics, and build errors are preserved). When you need the
complete, unfiltered output to confirm a claim (tests really passed, build is
really clean) rather than skim it, get the raw output instead of trusting the
summary:

- Run `rtk proxy <cmd>` to re-run the command with no filtering.
- Or, when the filtered output ends with `[full output: <path>]`, read that
file directly — it is the complete, unfiltered log already on disk.
14 changes: 13 additions & 1 deletion hooks/claude/rtk-awareness.md
Original file line number Diff line number Diff line change
Expand Up @@ -26,4 +26,16 @@ which rtk # Verify correct binary
All other commands are automatically rewritten by the Claude Code hook.
Example: `git status` → `rtk git status` (transparent, 0 tokens overhead)

Refer to CLAUDE.md for full command reference.
## Reading the full output

RTK output is a filtered summary — for most commands it keeps what matters
(test failures, panics, and build errors are preserved). When you need the
complete, unfiltered output to confirm a claim (tests really passed, build is
really clean) rather than skim it, get the raw output instead of trusting the
summary:

- Run `rtk proxy <cmd>` to re-run the command with no filtering.
- Or, when the filtered output ends with `[full output: <path>]`, read that
file directly — it is the complete, unfiltered log already on disk.

Run `rtk --help` for the full command reference.
12 changes: 12 additions & 0 deletions hooks/cline/rules.md
Original file line number Diff line number Diff line change
Expand Up @@ -30,3 +30,15 @@ rtk proxy <cmd> # Run raw (no filtering, for debugging)
## Why

RTK filters and compresses command output before it reaches the LLM context, saving 60-90% tokens on common operations. Always use `rtk <cmd>` instead of raw commands.

## Reading the full output

RTK output is a filtered summary — for most commands it keeps what matters
(test failures, panics, and build errors are preserved). When you need the
complete, unfiltered output to confirm a claim (tests really passed, build is
really clean) rather than skim it, get the raw output instead of trusting the
summary:

- Run `rtk proxy <cmd>` to re-run the command with no filtering.
- Or, when the filtered output ends with `[full output: <path>]`, read that
file directly — it is the complete, unfiltered log already on disk.
12 changes: 12 additions & 0 deletions hooks/codex/rtk-awareness.md
Original file line number Diff line number Diff line change
Expand Up @@ -30,3 +30,15 @@ rtk --version
rtk gain
which rtk
```

## Reading the full output

RTK output is a filtered summary — for most commands it keeps what matters
(test failures, panics, and build errors are preserved). When you need the
complete, unfiltered output to confirm a claim (tests really passed, build is
really clean) rather than skim it, get the raw output instead of trusting the
summary:

- Run `rtk proxy <cmd>` to re-run the command with no filtering.
- Or, when the filtered output ends with `[full output: <path>]`, read that
file directly — it is the complete, unfiltered log already on disk.
12 changes: 12 additions & 0 deletions hooks/copilot/rtk-awareness.md
Original file line number Diff line number Diff line change
Expand Up @@ -58,3 +58,15 @@ When Copilot CLI adds `updatedInput` support, only `rtk hook` needs updating —
| GitHub Copilot CLI | `PreToolUse` deny-with-suggestion | Denial + retry | `.github/hooks/rtk-rewrite.json` |
| OpenCode | Plugin `tool.execute.before` | Transparent rewrite | `hooks/opencode-rtk.ts` |
| (any) | Custom instructions | Prompt-level guidance | `.github/copilot-instructions.md` |

## Reading the full output

RTK output is a filtered summary — for most commands it keeps what matters
(test failures, panics, and build errors are preserved). When you need the
complete, unfiltered output to confirm a claim (tests really passed, build is
really clean) rather than skim it, get the raw output instead of trusting the
summary:

- Run `rtk proxy <cmd>` to re-run the command with no filtering.
- Or, when the filtered output ends with `[full output: <path>]`, read that
file directly — it is the complete, unfiltered log already on disk.
12 changes: 12 additions & 0 deletions hooks/kilocode/rules.md
Original file line number Diff line number Diff line change
Expand Up @@ -30,3 +30,15 @@ rtk proxy <cmd> # Run raw (no filtering, for debugging)
## Why

RTK filters and compresses command output before it reaches the LLM context, saving 60-90% tokens on common operations. Always use `rtk <cmd>` instead of raw commands.

## Reading the full output

RTK output is a filtered summary — for most commands it keeps what matters
(test failures, panics, and build errors are preserved). When you need the
complete, unfiltered output to confirm a claim (tests really passed, build is
really clean) rather than skim it, get the raw output instead of trusting the
summary:

- Run `rtk proxy <cmd>` to re-run the command with no filtering.
- Or, when the filtered output ends with `[full output: <path>]`, read that
file directly — it is the complete, unfiltered log already on disk.
12 changes: 12 additions & 0 deletions hooks/windsurf/rules.md
Original file line number Diff line number Diff line change
Expand Up @@ -30,3 +30,15 @@ rtk proxy <cmd> # Run raw (no filtering, for debugging)
## Why

RTK filters and compresses command output before it reaches the LLM context, saving 60-90% tokens on common operations. Always use `rtk <cmd>` instead of raw commands.

## Reading the full output

RTK output is a filtered summary — for most commands it keeps what matters
(test failures, panics, and build errors are preserved). When you need the
complete, unfiltered output to confirm a claim (tests really passed, build is
really clean) rather than skim it, get the raw output instead of trusting the
summary:

- Run `rtk proxy <cmd>` to re-run the command with no filtering.
- Or, when the filtered output ends with `[full output: <path>]`, read that
file directly — it is the complete, unfiltered log already on disk.