From cc-harness
Compresses long agent conversations into a nine-part structured summary preserving request, files, errors, user messages, and next steps.
How this skill is triggered — by the user, by Claude, or both
Slash command
/cc-harness:structured-context-compressorThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Use this skill when a free-form summary is too lossy and you need a reliable continuation artifact.
Use this skill when a free-form summary is too lossy and you need a reliable continuation artifact.
Render the standard template:
python3 {baseDir}/scripts/render_template.py
Then apply the prompt in references/prompt-template.md.
Preserve all user messages or an accurate equivalent. Do not compress away the corrections that changed the direction of work.
python3 {baseDir}/scripts/render_template.pynpx claudepluginhub learnprompt/cc-harness-skills --plugin cc-harnessCompresses agent session context using structured summarization strategies (anchored iterative, opaque, regenerative) to optimize tokens per task while preserving decisions, file changes, and next actions.
Optimizes context compression for agent sessions with tokens-per-task focus. Covers anchored iterative summarization, opaque compression, and regenerative full summary.
Designs and evaluates context compression strategies for long-running agent sessions. Use when agents exceed memory limits, need conversation summarization, or optimize tokens-per-task.