oliver-kriska/claude-elixir-phoenix / plugins/elixir-phoenix/skills/mix-compression
mix-compression
VerifiedReduce mix output noise (5-15% token savings) by installing rtk filters that compress mix test/credo/dialyzer/compile output before it reaches Claude. Use when long mix output floods context.
Mix Output Compression
Mix commands (mix test, mix credo, mix dialyzer, mix compile) emit
verbose, repetitive output that consumes context fast. This skill installs
rtk — a CLI proxy that filters tool output
before it lands in the transcript.
The filters short-circuit happy paths to a single line (mix test: all pass)
while preserving full failure blocks, compile errors, and stack traces. Net win:
5-15% per-session token reduction on mix-heavy workflows.
When to use
- Long sessions —
/phx:workor/phx:fullhitting context limits from mix output - Debugging loops —
/phx:investigateretryingmix compile/mix testrepeatedly - Dialyzer-heavy projects —
mix dialyzeroutput dominates the transcript
Iron Laws
- NEVER strip critical signals — compile errors (
** (CompileError),== Compilation error in), test failures (FAILURES,0 failures— preserved even on short-circuit), dialyzer warnings, and stack traces withfile:lineMUST pass through unchanged - Verify after install — run
rtk verify(orrtk verify --filter mix-test) to confirm the bundled test fixtures pass before declaring success - Never overwrite existing
.rtk/filters.toml— diff and merge instead
Workflow
Step 1: Detect rtk
which rtk && rtk --version
Read ${CLAUDE_SKILL_DIR}/references/install.md if rtk is missing — covers
homebrew install + shell hook setup.
Step 2: Seed .rtk/filters.toml
Reference filters live at ${CLAUDE_SKILL_DIR}/references/rtk-filters.toml. Six
production-tested filters covering:
mix-test— short-circuits all-pass, preserves failure blocks + compile errorsmix-credo— collapses clean runs, preserves violation blocksmix-dialyzer— drops PLT progress, keeps warnings + summarymix-deps-get— collapses unchanged package listsmix-ecto-migrate— strips compile prefix, short-circuits "already up"mix-compile— handles parallel worker prefixes (N>) and MIX_ENV
Run this if the project has no .rtk/filters.toml yet:
mkdir -p .rtk
cp "${CLAUDE_SKILL_DIR}/references/rtk-filters.toml" .rtk/filters.toml
Read both files if one already exists. Present a diff to the user. Merge only the filters they don't already have.
Step 3: Verify filters work
rtk verify # runs all embedded [[tests.*]] fixtures
rtk verify --filter mix-test # one filter only
Check that all report "passed". Flag and stop if any fail — usually means the user has a custom rtk version with regex differences.
Step 4: Confirm shell hook
Run rtk init zsh (or rtk init bash) to install the transparent rewrite hook
that turns mix X into rtk mix X. Re-running is safe (idempotent). Skip this
step and mix calls run unfiltered.
Customization
Add custom regex patterns to strip_lines_matching for project-specific noise
sources (e.g., third-party hex deps spamming stack traces). See the inline
example in ${CLAUDE_SKILL_DIR}/references/rtk-filters.toml lines 57-59.
What this is NOT
- Not a hook — Claude Code's
PostToolUsehooks fire after the tool result is in the transcript and cannot shrink it. rtk works at the subprocess layer (the only layer where transcript-shortening is possible). - Not project-analysis — the bundled filter set is universal across Phoenix
projects. No
mix.exsinspection needed. - Not telemetry — rtk has telemetry off by default (
enabled = falseinconfig.toml). Filters run locally, no data leaves the machine.
References
${CLAUDE_SKILL_DIR}/references/rtk-filters.toml— bundled filter set${CLAUDE_SKILL_DIR}/references/install.md— rtk install + shell hook setup- rtk on GitHub
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| finishing-a-development-branchobra/superpowersUse when implementation is complete, all tests pass, and you need to decide how to integrate the work | Stars: 319k | Updated | Claude CodeCodex | Verified | Install |
| systematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixes | Stars: 319k | Updated | Claude CodeCodex | Verified | Install |
| test-driven-developmentobra/superpowersUse when implementing any feature or bugfix, before writing implementation code | Stars: 319k | Updated | Claude CodeCodex | Verified | Install |
| skill-creatoranthropics/skillsCreate new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy. | Stars: 196k | Updated | Claude CodeCodex | Verified | Install |