kdeps-harness-compaction-user
v1.0.1kdeps harness: compaction-user
set harness / shelf context
PurposeThe text kdeps sends the model in agent mode: the sections of the system prompt, and the prompts behind compaction, goals, judges, prompt refinement and nudges.
LLM context: ~294 tokens when loaded (prompt or tool definition)
Where it runs
Part of the harness set, used in workflow and agent mode. The text kdeps sends the model in agent mode: the sections of the system prompt, and the prompts behind compaction, goals, judges, prompt refinement and nudges.
- you type a prompt
- the agent loop builds the request
- the harness sections become the system promptharness/compaction-user
- the model answers
- the loop runs tools or replies
Loaded by: kdeps (agent loop), /settings, kdeps run, kdeps konfig export, kdeps knowledge build, kdeps konfig import
In the code: kdeps (agent loop)agent.Newagent.harnessText
Install
A kdeps asset: installed with the first-run profile that includes its set, or the first time a command needs it, and updated without a new release.
Pin a version with kdeps install harness/compaction-user@<version>.
Contents
- name
- compaction-user
- kind
- standalone
The messages above are a conversation to summarize. Create a structured context checkpoint summary that another LLM will use to continue the work. Use this EXACT format. Do not write a "Summary" title. Every heading needs text under it; write "(none)" instead of a blank section. ## Goal must say what the user is trying to accomplish. ## Goal [What is the user trying to accomplish? Can be multiple items if the session covers different tasks.] ## Constraints & Preferences - [Any constraints, preferences, or requirements mentioned by user] - [Or "(none)" if none were mentioned] ## Progress ### Done - [x] [Completed tasks/changes] ### In Progress - [ ] [Current work] ### Blocked - [Issues preventing progress, if any] ## Key Decisions - **[Decision]**: [Brief rationale] ## Mistakes - [What went wrong and what it taught, or "(none)"] ## Wins - [What worked well and is worth repeating, or "(none)"] ## Next Steps 1. [Ordered list of what should happen next] ## Critical Context - [Any data, examples, or references needed to continue] - [Or "(none)" if not applicable] Keep each section concise. Preserve exact file paths, function names, and error messages.
version: 1.0.1
name: compaction-user
kind: standalone
body: |-
The messages above are a conversation to summarize. Create a structured context checkpoint summary that another LLM will use to continue the work.
Use this EXACT format. Do not write a "Summary" title. Every heading needs text under it; write "(none)" instead of a blank section. ## Goal must say what the user is trying to accomplish.
## Goal
[What is the user trying to accomplish? Can be multiple items if the session covers different tasks.]
## Constraints & Preferences
- [Any constraints, preferences, or requirements mentioned by user]
- [Or "(none)" if none were mentioned]
## Progress
### Done
- [x] [Completed tasks/changes]
### In Progress
- [ ] [Current work]
### Blocked
- [Issues preventing progress, if any]
## Key Decisions
- **[Decision]**: [Brief rationale]
## Mistakes
- [What went wrong and what it taught, or "(none)"]
## Wins
- [What worked well and is worth repeating, or "(none)"]
## Next Steps
1. [Ordered list of what should happen next]
## Critical Context
- [Any data, examples, or references needed to continue]
- [Or "(none)" if not applicable]
Keep each section concise. Preserve exact file paths, function names, and error messages.
Versions
| Version | Published | Status |
|---|---|---|
| 1.0.1 | 10/15/2026 | active |
| 1.0.0 | 10/11/2026 | active |
Details
- Author
- kdeps
- License
- Apache-2.0
- Latest Version
- 1.0.1
- Published
- 10/11/2026