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/ASCIT31/Dark-MoonWrote 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/ascit31/dark-moon/messaging-cache)<a href="https://agentmods.dev/agents/ascit31/dark-moon/messaging-cache"><img src="https://agentmods.dev/badge/agents/ascit31/dark-moon/messaging-cache/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/ascit31/dark-moon/messaging-cache"><img src="https://agentmods.dev/badge/agents/ascit31/dark-moon/messaging-cache.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00056 | $0.07262 |
| Opus 5.5 | $0.00022 | $0.02905 |
| Sonnet 5.5 | $0.00011 | $0.01452 |
| Haiku 4.5 | $0.00006 | $0.00726 |
Grade A, and why
messaging-cache scanned grade A with 2 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 1mo ago.
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.
Sends data to an external URLlowData exfiltration
A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.
- curl -s -u $USER:$PASS "http://$HOST:15672/api/queues/<vhost>/<queue>/get" -X POST -d '{"count":5,"ackmode":"ack_requeue_true","encoding":"auto"}' | jq . Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
Use redis-cli (already in the toolbox) for Redis, and curl+jq against the The source is not reproduced here
Licensed GPL-3.0
The repository is licensed GPL-3.0, which this catalogue does not treat as permission to reproduce the file. Read it at the source.
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.
- 1mo ago First seen · 547 lines · 56 tokens per session scan A 32e6e4d59c7d
messaging-cache is an agent published in the GitHub repository ASCIT31/Dark-Moon (1,031 stars, last pushed 16d ago), licensed GPL-3.0. It adds 56 tokens to every session and 7,262 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 2 findings (sends data to an external url, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
Environment Inspector
Background Snowflake environment scanner. Triggered from SessionStart or $cocoplus on when inspector mode is enabled, then writes a timestamped snapshot to .cocoplus/snapshots/.
qdrant-expert
Configure and operate the vector store in production. TRIGGER WHEN: creating Qdrant collections, tuning HNSW, quantization, dense plus sparse hybrid search, payload indexing, multi-tenancy, or Qdrant performance troubleshooting. DO NOT TRIGGER WHEN: end-to-end RAG design, or another vector database such as Pinecone…
data
Use when designing database schemas, writing migrations, optimizing queries, or planning caching strategies.
network-recon-agent
Network reconnaissance subagent for red-run. Performs host discovery, port scanning, service enumeration, and quick-win checks as directed by the orchestrator. Has access to nmap via MCP server — no sudo handoff needed. Use when the orchestrator needs to scan a target or subnet.
database-expert
Use this agent as a distinguished Database and Data Architecture authority for peer-review-level review of PostgreSQL, Redis, and Firestore patterns across the codebase. Covers query optimization, schema design, migration safety, connection pooling, caching strategy, data modeling, consistency patterns, and polyglot…
redis-expert
Expert in Redis for in-memory data storage, caching, and real-time analytics.