diff --git a/hooks/antigravity/rules.md b/hooks/antigravity/rules.md index 8ee44bcd4..0d94fde75 100644 --- a/hooks/antigravity/rules.md +++ b/hooks/antigravity/rules.md @@ -30,3 +30,15 @@ rtk proxy # 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 ` 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 ` to re-run the command with no filtering. +- Or, when the filtered output ends with `[full output: ]`, read that + file directly — it is the complete, unfiltered log already on disk. diff --git a/hooks/claude/rtk-awareness.md b/hooks/claude/rtk-awareness.md index 0eaf3d52a..ff3315b8f 100644 --- a/hooks/claude/rtk-awareness.md +++ b/hooks/claude/rtk-awareness.md @@ -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 ` to re-run the command with no filtering. +- Or, when the filtered output ends with `[full output: ]`, read that + file directly — it is the complete, unfiltered log already on disk. + +Run `rtk --help` for the full command reference. diff --git a/hooks/cline/rules.md b/hooks/cline/rules.md index 7d6c8aff5..b9c32b843 100644 --- a/hooks/cline/rules.md +++ b/hooks/cline/rules.md @@ -30,3 +30,15 @@ rtk proxy # 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 ` 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 ` to re-run the command with no filtering. +- Or, when the filtered output ends with `[full output: ]`, read that + file directly — it is the complete, unfiltered log already on disk. diff --git a/hooks/codex/rtk-awareness.md b/hooks/codex/rtk-awareness.md index 7ae285e1a..b4f07a458 100644 --- a/hooks/codex/rtk-awareness.md +++ b/hooks/codex/rtk-awareness.md @@ -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 ` to re-run the command with no filtering. +- Or, when the filtered output ends with `[full output: ]`, read that + file directly — it is the complete, unfiltered log already on disk. diff --git a/hooks/copilot/rtk-awareness.md b/hooks/copilot/rtk-awareness.md index 185f460c5..afe750636 100644 --- a/hooks/copilot/rtk-awareness.md +++ b/hooks/copilot/rtk-awareness.md @@ -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 ` to re-run the command with no filtering. +- Or, when the filtered output ends with `[full output: ]`, read that + file directly — it is the complete, unfiltered log already on disk. diff --git a/hooks/kilocode/rules.md b/hooks/kilocode/rules.md index 53d764596..b2542e369 100644 --- a/hooks/kilocode/rules.md +++ b/hooks/kilocode/rules.md @@ -30,3 +30,15 @@ rtk proxy # 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 ` 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 ` to re-run the command with no filtering. +- Or, when the filtered output ends with `[full output: ]`, read that + file directly — it is the complete, unfiltered log already on disk. diff --git a/hooks/windsurf/rules.md b/hooks/windsurf/rules.md index 8491f5a78..f8f197265 100644 --- a/hooks/windsurf/rules.md +++ b/hooks/windsurf/rules.md @@ -30,3 +30,15 @@ rtk proxy # 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 ` 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 ` to re-run the command with no filtering. +- Or, when the filtered output ends with `[full output: ]`, read that + file directly — it is the complete, unfiltered log already on disk.