Stats
Actions
Tags
Help us improve
Share bugs, ideas, or general feedback.
From judges
Checks for cached plan-evaluation.json using file timestamps to skip redundant plan-evaluator launches in Phase 1.3. Returns EVAL_CACHE_HIT with values or EVAL_CACHE_MISS if stale.
npx claudepluginhub closedloop-ai/claude-plugins --plugin judgesHow this skill is triggered — by the user, by Claude, or both
Slash command
/judges:eval-cacheThis skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
Check whether a prior simple-mode evaluation can be reused, avoiding a redundant plan-evaluator launch when the plan has not changed.
Checks validity of prior Phase 2.5 critic reviews by hashing plan.json and critic-gates.json against stored hash, skipping redundant runs on cache hit.
Dispatches a reviewer subagent to validate plans structurally and for prose/design correctness before execution.
Reviews plans/specs against workspace codebase, verifying claims via file inspection and evaluating repo fit, technical correctness, scope, evaluation, and safety/ops. Supports focus modes and external judges.
Share bugs, ideas, or general feedback.
Check whether a prior simple-mode evaluation can be reused, avoiding a redundant plan-evaluator launch when the plan has not changed.
Activate this skill at the start of Phase 1.3 (Simple Mode Evaluation), before launching @code:plan-evaluator. If the cache is fresh, skip the evaluator entirely and use the cached result.
Run the cache check script. The scripts/ directory is relative to this skill's base directory (shown above as "Base directory for this skill"):
bash <base_directory>/scripts/check_eval_cache.sh <WORKDIR>
The script prints one of two structured results to stdout:
EVAL_CACHE_HIT
simple_mode: true|false
selected_critics: [critic1, critic2, ...]
summary: <cached evaluation summary>
Action: Parse simple_mode and selected_critics from the output. Skip launching @code:plan-evaluator and proceed with the cached values as if the evaluator had just returned them.
EVAL_CACHE_MISS
reason: <why the cache is stale or missing>
Action: Launch @code:plan-evaluator as normal. The evaluator will write a fresh plan-evaluation.json that subsequent iterations can cache from.
The script uses file modification timestamps:
plan-evaluation.json does not exist: missplan.json is newer than plan-evaluation.json: miss (plan was modified since last evaluation)plan-evaluation.json is newer than plan.json: hit (evaluation is still valid)This correctly handles the case where a user modifies the plan while the workflow is paused: editing plan.json updates its mtime, invalidating the cached evaluation.