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.
npx skills add ThreatRecall/zettelforge --skill claude-codegit clone --depth 1 https://github.com/ThreatRecall/zettelforgeWrote 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/skills/threatrecall/zettelforge/claude-code)<a href="https://agentmods.dev/skills/threatrecall/zettelforge/claude-code"><img src="https://agentmods.dev/badge/skills/threatrecall/zettelforge/claude-code/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/skills/threatrecall/zettelforge/claude-code"><img src="https://agentmods.dev/badge/skills/threatrecall/zettelforge/claude-code.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 | $0.00080 | $0.00970 |
| Opus 5.5 | $0.00032 | $0.00388 |
| Sonnet 5.5 | $0.00016 | $0.00194 |
| Haiku 4.5 | $0.00008 | $0.00097 |
Grade A, and why
zettelforge 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 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.
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 — 111 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ZettelForge: CTI Agentic Memory
Persistent memory system for cyber threat intelligence. 75% accuracy on CTI queries, 111ms p50 latency.
When to use this skill
- Storing threat intelligence from reports, incidents, or conversations
- Recalling what we know about a threat actor, CVE, tool, or campaign
- Synthesizing briefs from accumulated intelligence
- Looking up entity relationships (who uses what, who targets what)
- Traversing the STIX 2.1 knowledge graph
- Syncing from OpenCTI
Quick reference
Store intel
from zettelforge import MemoryManager
mm = MemoryManager()
note, status = mm.remember("APT28 uses Cobalt Strike via CVE-2024-1111", domain="cti")
Search memory
results = mm.recall("What tools does APT28 use?", k=10)
for r in results:
print(f"{r.id}: {r.content.raw[:100]}")
Entity lookup (fast, O(1))
mm.recall_actor("APT28") # or "Fancy Bear" — aliases resolve automatically
mm.recall_cve("CVE-2024-3094")
mm.recall_tool("cobalt-strike")
Synthesize answer
result = mm.synthesize("Summarize APT28 activity", format="synthesized_brief")
# formats: direct_answer, synthesized_brief, timeline_analysis, relationship_map
Graph traversal
paths = mm.traverse_graph("actor", "apt28", max_depth=2)
# APT28 → USES_TOOL → cobalt-strike → EXPLOITS_CVE → CVE-2024-1111
Ingest report (auto-chunks)
results = mm.remember_report(content="Full report text...", source_url="https://...", domain="cti")
Two-phase extraction (selective, deduplicating)
results = mm.remember_with_extraction("APT28 dropped DROPBEAR, now uses edge devices", domain="cti")
# Returns: [(<MemoryNote>, "added"), (<MemoryNote>, "updated"), ...]
OpenCTI sync
from zettelforge.opencti_sync import sync_opencti
stats = sync_opencti(mm, limit=50) # Pull latest from OpenCTI
MCP tools available
If the ZettelForge MCP server is configured, use these tools directly:
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 · 111 lines · 80 tokens per session scan A 0415c3eecdb0
zettelforge is a skill published in the GitHub repository ThreatRecall/zettelforge (66 stars, last pushed 2d ago), licensed MIT. It adds 80 tokens to every session and 970 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-09-11.
Other skills, from other repositories
qdrant
Vector search engine for production RAG systems.
dspy
DSPy: declarative LM programs, auto-optimize prompts, RAG.
chroma
Embedding database for RAG and semantic search.
pinecone
Managed vector DB for production RAG and search.
faiss
Fast vector similarity search at billion scale.
pinecone-research
Agent RAG and long-term memory with Pinecone.