What is critic-cache?

A review cache that records which plan and critic settings were reviewed, then checks whether they have changed before starting reviews again.

Use it before a critic-validation phase to decide whether to reuse existing review files or launch new critic agents.

It prevents repeated critic reviews when the plan is unchanged. A changed plan or review configuration causes the critics to run again.

critic-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 critic-cache

Clone the repo

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

Made for: Claude Code.

Or install code, the plugin that ships this one along with the rest of its 15 skills, 7 commands, 23 agents, 7 hooks.

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/critic-cache.svg)](https://agentmods.dev/skills/closedloop-ai/claude-plugins/critic-cache)

Your own site

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

Per session 79 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 543 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	$0.00079	$0.00543
Opus 5	$0.00039	$0.00271
Sonnet 5	$0.00016	$0.00109
Haiku 4.5	$0.00008	$0.00054

Measured yesterday against content hash 0b0ea859972f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

critic-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 yesterday.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/check_critic_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/code/skills/critic-cache/SKILL.md · 69 lines

What it actually says

Critic Cache

Check whether prior critic reviews are still valid, avoiding redundant Sonnet agent launches when the plan hasn't changed since the last critic run.

When to Use

Activate this skill at the start of Phase 2.5 (Critic Validation), before launching any critic agents. If the cache is fresh, skip the entire critic phase.

Usage

Run the cache check script:

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

Interpreting Output

Cache Hit

CRITIC_CACHE_HIT

Action: Skip all critic agent launches. Proceed directly to Phase 2.6 (or Phase 2.7 if no merge is needed). The existing $WORKDIR/reviews/*.review.json files are still valid.

Cache Miss

CRITIC_CACHE_MISS
reason: <why the cache is stale or missing>

Action: Run critics as normal. After all critics complete, stamp the cache:

if [ -f ".closedloop-ai/settings/critic-gates.json" ]; then
  cat $WORKDIR/plan.json .closedloop-ai/settings/critic-gates.json | shasum -a 256 > $WORKDIR/reviews/.plan-hash
else
  shasum -a 256 $WORKDIR/plan.json > $WORKDIR/reviews/.plan-hash
fi

How Freshness Works

The script hashes both plan.json and .closedloop-ai/settings/critic-gates.json (if it exists) into a single combined hash. This ensures:

Plan content changes → cache miss → critics re-run
Critic configuration changes (adding/removing critics) → cache miss → critics re-run
No changes → cache hit → critics skipped

Cache Conditions

Cache hit requires ALL of:

plan.json exists
reviews/ directory exists with at least 1 .review.json file
reviews/.plan-hash exists
Current combined hash matches stored hash

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_critic_cache.sh 2.1 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.

yesterday First seen · 69 lines · 79 tokens per session scan A 0b0ea859972f

Subscribe to this mod's changes

critic-cache is a skill published in the GitHub repository closedloop-ai/claude-plugins (103 stars, last pushed yesterday), licensed Apache-2.0. It adds 79 tokens to every session and 543 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.

Code review 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

pr-babysitter

Monitors or repairs an open GitHub PR: CI failures, conflicts, review threads, and merge readiness, reporting state changes. Use when asked to "watch this PR", "fix CI", "resolve conflicts", or "address review comments". For PR metadata use pr-creator; for npm release PRs use autoship.

mblode/agent-skills · 72 tokens

dx-audit

Audits libraries, CLIs, and SDKs using 38 rules for public contracts, package exports, piped output, errors, and configuration. Use when asked to "audit my CLI", "review my SDK", "make this agent-friendly", or diagnose package type resolution. For agentic product trust use ax-audit; for docs use docs-writing.

mblode/agent-skills · 76 tokens

pr-creator

Creates or updates GitHub PRs with house-style titles and bodies, issue linking, repository templates, and draft state. Use when asked to "create a PR", "rewrite the PR description", or "polish this PR". For code fixes use tidy; for CI and review threads use pr-babysitter; for npm releases use autoship.

mblode/agent-skills · 75 tokens

tidy

Applies diff-scoped simplifications using reuse, ownership, efficiency, and test-value checks, including actionable review findings. Use when asked to "tidy this", "simplify my diff", or "apply the review findings". For a read-only report use pr-reviewer; for repository architecture use codebase-architecture.