mirror of
https://github.com/SHOGGOTH-SECTOR/sica-fondt.git
synced 2026-08-01 08:30:20 +00:00
24f816b6a3
Place useful parts of the surrounding repos into sica-fondt by layer, per the
body model (Ada = membrane; brain/endocrine/capabilities/knowledge non-Ada):
- brain/ LLM reasoning + providers (dapr, hermes, MoMoA)
- capabilities/ REPRAG sidecars: hermes tools/skills, dapr tools, parallel
dispatch, A51 channels, and the OSINT cluster
- knowledge/ LORAG corpus: 754 cyber-skills, agency personas, secure-coding,
MITRE ATT&CK data
- reference/ defensive threat-reference (C3, shhbruh doc) + AdaYaml parser
License handling: AGPL sources (worldosint, advanced_evolution, mercury,
Reticulum) and GPL DeTTECT are SPEC-only clean-room/port descriptions — no
copyleft code copied. MIT/Apache/data parts copied as working trees.
Safety: shhbruh escape/persistence material and C3 covert-C2 kept as reference
only, not wired into the running organism. See CONSOLIDATION.md.
https://claude.ai/code/session_01UehUqEXXJJCsHoA4voCU5c
9 lines
874 B
Markdown
9 lines
874 B
Markdown
---
|
|
name: "summarize-progress-start"
|
|
---
|
|
An LLM Agent is working on a project and it's taking a long time. I need to summarize the Latest Agent Update Message into a clear and concise summary that describes what the agent has done and what it's doing presented in the **first person** using the same tense as the Latest Agent Update Message. Your response MUST be fully grounded in the provided update. NEVER imagine, invent, or infer what work is being done. The Agent may invoke tools using the ${strings/tool-prefix}$ symbol. If you can understand what the tool request will do, and you can describe it in natural language you should, but you MUST NOT include the tool request itself. Ignore the tool request if it doesn't make sense to you.
|
|
|
|
Your update should be a short paragraph of one to three sentences.
|
|
|
|
**Latest Agent Update Message:**
|
|
${LastOrchestratorResponse} |