saint-graves/sica-fondt
1
0
Fork 0
mirror of https://github.com/SHOGGOTH-SECTOR/sica-fondt.git synced 2026-08-01 00:23:15 +00:00
Code Issues Packages Projects Releases Wiki Activity
sica-fondt/brain/reasoning/momoa/assets/prompts/strings/summary-xml-prompt.md
Claude 24f816b6a3
Consolidate 22 sibling repos into layered organism structure 
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
2026-06-10 06:53:01 +00:00

1.5 KiB
Raw Blame History

name
summaryXMLPrompt

Generate a final project summary in valid XML format based on the provided XML summary, and the following specific instructions.

The XML must have a root element named '

'. It must contain the following child elements:

  • : A summary of the project's outcome or main deliverable.
  • <WORK_SUMMARY>: A retrospective summary of the work performed by the experts.
  • <USER_FEEDBACK>: Feedback intended for the user about the project outcome.
  • <DEV_FEEDBACK>: Feedback intended for the agent/tool developers about the process.
  • : A list of files that were produced or significantly modified. Each file should be represented by a element containing a <FILE_NAME> element with the filename as its text content and a element with a brief description of the file's contents.
  • <MODEL_USE>: A summary of how many times each LLM API/Model pair was invoked during the process.

Ensure the content within the , <WORK_SUMMARY>, <USER_FEEDBACK>, and <DEV_FEEDBACK> tags is plain text (avoiding internal XML tags unless properly escaped or in CDATA). The section should list all the files that were produced, based on the available files.

Here is the required structure for the <MODEL_USE> element. Include this structure as a child of the

element, with appropriate line breaks and indentation to make it easy to read: ${messageCountsXml}

The final response from the orchestrator provided below: ${finalOrchestratorResult}

Generate the complete XML summary now, starting with the

tag.