A cache check for a previous plan-evaluation result. It tells an orchestration workflow whether the saved result can be reused or whether a new plan evaluator should run.

Use it during a simple-mode plan evaluation to check the evaluation cache before launching another evaluation agent.

It avoids repeating an evaluation when the plan has not changed, while detecting when the saved result is missing or out of date.

eval-cache — Skill for Claude Code by closedloop-ai

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent

npx skills add closedloop-ai/claude-plugins --skill eval-cache

Clone the repo

git clone --depth 1 https://github.com/closedloop-ai/claude-plugins

Made for: Claude Code.

Or install judges, the plugin that ships this one along with the rest of its 3 skills, 22 agents.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/closedloop-ai/claude-plugins/eval-cache.svg)](https://agentmods.dev/skills/closedloop-ai/claude-plugins/eval-cache)

Your own site

<a href="https://agentmods.dev/skills/closedloop-ai/claude-plugins/eval-cache"><img src="https://agentmods.dev/badge/skills/closedloop-ai/claude-plugins/eval-cache.svg" alt="Measured on agentmods" height="20"></a>

Per session 82 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 487 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00082	$0.00487
Opus 5	$0.00041	$0.00244
Sonnet 5	$0.00016	$0.00097
Haiku 4.5	$0.00008	$0.00049

Measured today against content hash 2f28602bce1c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

eval-cache scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/check_eval_cache.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugins/judges/skills/eval-cache/SKILL.md · 60 lines

What it actually says

Eval Cache

Check whether a prior simple-mode evaluation can be reused, avoiding a redundant plan-evaluator launch when the plan has not changed.

When to Use

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.

Usage

Run the cache check script:

bash ${CLAUDE_SKILL_DIR}/scripts/check_eval_cache.sh <WORKDIR>

Interpreting Output

The script prints one of two structured results to stdout:

Cache Hit

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.

Cache Miss

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.

How Freshness Works

The script uses file modification timestamps:

If plan-evaluation.json does not exist: miss
If plan.json is newer than plan-evaluation.json: miss (plan was modified since last evaluation)
If 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.

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

scripts/check_eval_cache.sh 1.8 KB runs code

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

today First seen · 60 lines · 82 tokens per session scan A 2f28602bce1c

Subscribe to this mod's changes

eval-cache is a skill published in the GitHub repository closedloop-ai/claude-plugins (103 stars, last pushed yesterday), licensed Apache-2.0. It adds 82 tokens to every session and 487 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-07.

Building agents LLM Planning agentic-ai ai-agents anthropic developer-tools

pr-reviewer

Reviews a diff or security scope read-only using evidence-tiered findings, structural and context-error rubrics, and repository review policy. Use when asked to "review my changes", "structural review", "review for AI patterns", or "security audit". For applying fixes use tidy; for UI defects use ui-design.

mblode/agent-skills · 68 tokens

autoship

Runs a changesets npm release through the version PR, CI publish, and registry verification. Use when asked to "release this package", "autoship", "merge Version Packages", or diagnose a release that did not publish. For feature PRs use pr-creator or pr-babysitter.

mblode/agent-skills · 63 tokens

scaffold-cli

Scaffolds a TypeScript CLI and npm package with the house toolchain, dual tsdown outputs, CLI contracts, changesets, and publishing templates. Use when asked to "scaffold a CLI" or "start an npm package". For an existing package release use autoship; for existing API ergonomics use dx-audit.

mblode/agent-skills · 71 tokens

eval-cache