a11y-pass
FreeCatch the accessibility failures that ship in almost every AI-built UI. Use after building any interactive component.
The English summary is being prepared. Showing the original description.
Archive228/loopkit755Updated Jul 15, 2026
FreePublished on GitHub
model-routing
Split the Plan/Act/Verify loop across three model tiers — frontier planner, cheap executor, frontier judge — via env vars read by run.sh.
The English summary is being prepared. Showing the original description.
See how to installFiles included (1)
- SKILL.md1.8 KB
SKILL.md (original)
Review the instructions the agent will receive before you install.
Model routing
run.sh reads three optional env vars and threads them into each claude invocation as --model. All default to unset, in which case the CLI default model is used (behaviour unchanged from a bare run).
The three knobs
CLAUDE_PLANNER_MODEL— reserved for/specworkflows that draft PROMPT.md up front. Not read by the currentrun.shloop, but claimed here so future planner passes bind to it.CLAUDE_EXECUTOR_MODEL— used on the "do the next step" call. This is the workhorse; it runs on every iteration. Pick something cheap and fast.CLAUDE_JUDGE_MODEL— used on the/verifycall. Runs once per iteration to adversarially check the executor's diff. Pick a frontier model — a weak judge is worse than no judge.
Recommended shape
planner = frontier (Opus-class, runs once at /spec time)
executor = cheap-fast (Haiku-class, runs every turn)
judge = frontier (Opus-class, runs every turn but on a small diff)
Example
export CLAUDE_PLANNER_MODEL="claude-opus-4-7"
export CLAUDE_EXECUTOR_MODEL="claude-haiku-4-7"
export CLAUDE_JUDGE_MODEL="claude-opus-4-7"
./run.sh
The Elvis Executor+Judge finding
A cheap executor paired with a frontier judge outperforms a frontier executor with no judge on long loops. The judge catches the executor's premature-victory claims that a mono-model run rationalises away when it runs out of context. Cost stays low because the judge only sees the diff, not the working history.
Reviews
No reviews yet. Tell others what you thought.
Comments
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
More skills from this repository
Before compaction Loopkit extracts decisions into claude-decisions.json (machine-readable). Read it alongside claude-progress.txt at session start — prose is for humans, JSON is for the loop.
The English summary is being prepared. Showing the original description.
Archive228/loopkit755Updated Jul 15, 2026
Review a diff against the goal spec assuming the code is BROKEN. The reviewer that lives in the maker's head always agrees with itself — this pulls review into a hostile, separate pass. Invoke after every code change before marking work done.
The English summary is being prepared. Showing the original description.
Archive228/loopkit755Updated Jul 15, 2026
authz-check
FreeVerify that an endpoint checks ownership, not just authentication. Use on any handler that reads or mutates user data.
The English summary is being prepared. Showing the original description.
Archive228/loopkit755Updated Jul 15, 2026
Find the exact commit that introduced a bug. Use when something worked before and broke, and you don't know which change did it.
The English summary is being prepared. Showing the original description.
Archive228/loopkit755Updated Jul 15, 2026
Before picking new work, smoke-test the last "completed" feature. If it's broken, revert and re-open it before touching anything else. Kills the "looks shipped, isn't shipped" bug across sessions.
The English summary is being prepared. Showing the original description.
Archive228/loopkit755Updated Jul 15, 2026