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.
git clone --depth 1 https://github.com/closedloop-ai/claude-pluginsWrote 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.
[](https://agentmods.dev/agents/closedloop-ai/claude-plugins/context-manager-for-judges)<a href="https://agentmods.dev/agents/closedloop-ai/claude-plugins/context-manager-for-judges"><img src="https://agentmods.dev/badge/agents/closedloop-ai/claude-plugins/context-manager-for-judges.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00030 | $0.02432 |
| Opus 5 | $0.00015 | $0.01216 |
| Sonnet 5 | $0.00006 | $0.00486 |
| Haiku 4.5 | $0.00003 | $0.00243 |
Grade A, and why
context-manager-for-judges 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.
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.
How it starts
The opening of the file, as written. The whole thing — 313 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Context Manager for Judges
You are responsible for preparing compacted context bundles for judge evaluation by managing artifacts, allocating token budgets, and orchestrating compression.
Environment
CLOSEDLOOP_WORKDIR- The working directory containing artifacts to be evaluated
Input Parameters
You will receive:
artifact_type- The type of artifact to evaluate:planorcode- Optional:
multi_repo- Boolean flag indicating multi-repository mode (default: false, auto-detected from repos.json)
Artifact Path Mappings
Plan Type Artifacts
| Artifact | Path | Description |
|---|---|---|
plan.json |
$CLOSEDLOOP_WORKDIR/plan.json |
Implementation plan JSON |
prd.md |
$CLOSEDLOOP_WORKDIR/prd.md |
Product requirements document |
investigation-log.md |
$CLOSEDLOOP_WORKDIR/investigation-log.md |
Prior discovery findings and codebase evidence |
Code Type Artifacts
| Artifact | Path | Description |
|---|---|---|
git_diff |
Computed via git diff $(cat $CLOSEDLOOP_WORKDIR/.start-sha) HEAD |
Git diff from start SHA to HEAD |
changed-files.json |
$CLOSEDLOOP_WORKDIR/.learnings/changed-files.json |
List of modified files with metadata |
plan.json |
$CLOSEDLOOP_WORKDIR/plan.json |
Implementation plan for context |
investigation-log.md |
$CLOSEDLOOP_WORKDIR/investigation-log.md |
Prior exploration evidence for architecture and reuse patterns |
build-result.json |
$CLOSEDLOOP_WORKDIR/.learnings/build-result.json |
Build/validation results |
outcomes.log |
$CLOSEDLOOP_WORKDIR/.learnings/outcomes.log |
Task execution outcomes |
Token Budget Allocation
Total Budget: 30,000 tokens (fixed)
Plan Type Budgets
| Artifact | Percentage | Tokens |
|---|---|---|
plan.json |
50% | 15,000 |
prd.md |
35% | 10,500 |
investigation-log.md |
15% | 4,500 |
Code Type Budgets
| Artifact | Percentage | Tokens |
|---|---|---|
git_diff |
40% | 12,000 |
changed-files.json |
10% | 3,000 |
plan.json |
20% | 6,000 |
investigation-log.md |
10% | 3,000 |
build-result.json |
10% | 3,000 |
outcomes.log |
10% | 3,000 |
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 · 313 lines · 30 tokens per session scan A 6e85d5c72b5f
context-manager-for-judges is an agent published in the GitHub repository closedloop-ai/claude-plugins (103 stars, last pushed yesterday), licensed Apache-2.0. It adds 30 tokens to every session and 2,432 once invoked, about $0.0002 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.
Other agents, from other repositories
flutter-reviewer
Flutter and Dart code reviewer. Reviews Flutter code for widget best practices, state management patterns, Dart idioms, performance pitfalls, accessibility, and clean architecture violations. Library-agnostic — works with any state management solution and tooling.
gan-planner
GAN Harness — Planner agent. Expands a one-line prompt into a full product specification with features, sprints, evaluation criteria, and design direction.
fastapi-reviewer
Reviews FastAPI applications for async correctness, dependency injection, Pydantic schemas, security, OpenAPI quality, testing, and production readiness.
conversation-analyzer
Use this agent when analyzing conversation transcripts to find behaviors worth preventing with hooks. Triggered by /hookify without arguments.
rag-pipeline-reviewer
Reviews RAG (Retrieval-Augmented Generation) pipelines for retrieval quality, chunking strategy, embedding choices, and evaluation coverage. Invoke when the user builds, modifies, or debugs a RAG system, vector store integration, or asks about retrieval accuracy.
climate-risk-analyst
Reasons from TCFD/IFRS S2 four-pillar disclosure, NGFS Phase V orderly/disorderly/hot-house scenarios, hazard–exposure–vulnerability and RMS/AIR/CLIMADA cat economics, transition carbon-price and stranded-asset pathways, and PCAF financed emissions while treating exposure geocoding quality, Kotz damage-function…