// Design and evaluate context compression strategies for long-running agent sessions. Use when agents exhaust memory, need to summarize conversation history, or when optimizing tokens-per-task rather than tokens-per-request.
| name | context-compression |
| description | Design and evaluate context compression strategies for long-running agent sessions. Use when agents exhaust memory, need to summarize conversation history, or when optimizing tokens-per-task rather than tokens-per-request. |
When agent sessions generate millions of tokens of conversation history, compression becomes mandatory. The naive approach is aggressive compression to minimize tokens per request. The correct optimization target is tokens per task: total tokens consumed to complete a task, including re-fetching costs when compression loses critical information.
Activate this skill when:
Context compression trades token savings against information loss. Three production-ready approaches exist:
Anchored Iterative Summarization: Maintain structured, persistent summaries with explicit sections for session intent, file modifications, decisions, and next steps. When compression triggers, summarize only the newly-truncated span and merge with the existing summary. Structure forces preservation by dedicating sections to specific information types.
Opaque Compression: Produce compressed representations optimized for reconstruction fidelity. Achieves highest compression ratios (99%+) but sacrifices interpretability. Cannot verify what was preserved.
Regenerative Full Summary: Generate detailed structured summaries on each compression. Produces readable output but may lose details across repeated compression cycles due to full regeneration rather than incremental merging.
The critical insight: structure forces preservation. Dedicated sections act as checklists that the summarizer must populate, preventing silent information drift.
Traditional compression metrics target tokens-per-request. This is the wrong optimization. When compression loses critical details like file paths or error messages, the agent must re-fetch information, re-explore approaches, and waste tokens recovering context.
The right metric is tokens-per-task: total tokens consumed from task start to completion. A compression strategy saving 0.5% more tokens but causing 20% more re-fetching costs more overall.
Artifact trail integrity is the weakest dimension across all compression methods, scoring 2.2-2.5 out of 5.0 in evaluations. Even structured summarization with explicit file sections struggles to maintain complete file tracking across long sessions.
Coding agents need to know:
This problem likely requires specialized handling beyond general summarization: a separate artifact index or explicit file-state tracking in agent scaffolding.
Effective structured summaries include explicit sections:
## Session Intent
[What the user is trying to accomplish]
## Files Modified
- auth.controller.ts: Fixed JWT token generation
- config/redis.ts: Updated connection pooling
- tests/auth.test.ts: Added mock setup for new config
## Decisions Made
- Using Redis connection pool instead of per-request connections
- Retry logic with exponential backoff for transient failures
## Current State
- 14 tests passing, 2 failing
- Remaining: mock setup for session service tests
## Next Steps
1. Fix remaining test failures
2. Run full test suite
3. Update documentation
This structure prevents silent loss of file paths or decisions because each section must be explicitly addressed.
When to trigger compression matters as much as how to compress:
| Strategy | Trigger Point | Trade-off |
|---|---|---|
| Fixed threshold | 70-80% context utilization | Simple but may compress too early |
| Sliding window | Keep last N turns + summary | Predictable context size |
| Importance-based | Compress low-relevance sections first | Complex but preserves signal |
| Task-boundary | Compress at logical task completions | Clean summaries but unpredictable timing |
The sliding window approach with structured summaries provides the best balance of predictability and quality for most coding agent use cases.
Traditional metrics like ROUGE or embedding similarity fail to capture functional compression quality. A summary may score high on lexical overlap while missing the one file path the agent needs.
Probe-based evaluation directly measures functional quality by asking questions after compression:
| Probe Type | What It Tests | Example Question |
|---|---|---|
| Recall | Factual retention | "What was the original error message?" |
| Artifact | File tracking | "Which files have we modified?" |
| Continuation | Task planning | "What should we do next?" |
| Decision | Reasoning chain | "What did we decide about the Redis issue?" |
If compression preserved the right information, the agent answers correctly. If not, it guesses or hallucinates.
Six dimensions capture compression quality for coding agents:
Accuracy shows the largest variation between compression methods (0.6 point gap). Artifact trail is universally weak (2.2-2.5 range).
Use anchored iterative summarization when:
Use opaque compression when:
Use regenerative summaries when:
| Method | Compression Ratio | Quality Score | Trade-off |
|---|---|---|---|
| Anchored Iterative | 98.6% | 3.70 | Best quality, slightly less compression |
| Regenerative | 98.7% | 3.44 | Good quality, moderate compression |
| Opaque | 99.3% | 3.35 | Best compression, quality loss |
The 0.7% additional tokens retained by structured summarization buys 0.35 quality points. For any task where re-fetching costs matter, this trade-off favors structured approaches.
Example 1: Debugging Session Compression
Original context (89,000 tokens, 178 messages):
Structured summary after compression:
## Session Intent
Debug 401 Unauthorized error on /api/auth/login despite valid credentials.
## Root Cause
Stale Redis connection in session store. JWT generated correctly but session could not be persisted.
## Files Modified
- auth.controller.ts: No changes (read only)
- middleware/cors.ts: No changes (examined)
- config/redis.ts: Fixed connection pooling configuration
- services/session.service.ts: Added retry logic for transient failures
- tests/auth.test.ts: Updated mock setup
## Test Status
14 passing, 2 failing (mock setup issues)
## Next Steps
1. Fix remaining test failures (mock session service)
2. Run full test suite
3. Deploy to staging
Example 2: Probe Response Quality
After compression, asking "What was the original error?":
Good response (structured summarization):
"The original error was a 401 Unauthorized response from the /api/auth/login endpoint. Users received this error with valid credentials. Root cause was stale Redis connection in session store."
Poor response (aggressive compression):
"We were debugging an authentication issue. The login was failing. We fixed some configuration problems."
The structured response preserves endpoint, error code, and root cause. The aggressive response loses all technical detail.
This skill connects to several others in the collection:
Internal reference:
Related skills in this collection:
External resources:
Created: 2025-12-22 Last Updated: 2025-12-22 Author: Agent Skills for Context Engineering Contributors Version: 1.0.0
Generate minimal HTML pages to review Claude Code output in a browser. Use when terminal output is hard to read, when reviewing lists/tables/drafts, or when user says "show me", "make this reviewable", "quick view", or "open as webpage". Produces unstyled semantic HTML only.
Master LLM-as-a-Judge evaluation techniques including direct scoring, pairwise comparison, rubric generation, and bias mitigation. Use when building evaluation systems, comparing model outputs, or establishing quality standards for AI-generated content.
Build a design system from scratch using the Design Graph methodology. Use when starting a component library, creating design tokens, establishing typography scales, or structuring a theme. Based on Brent Jackson's (jxnblk) constraint-based systems.
Automatically creates user-facing changelogs from git commits by analyzing commit history, categorizing changes, and transforming technical commits into clear, customer-friendly release notes. Turns hours of manual changelog writing into minutes of automated generation.
This skill should be used when user wants to learn from their collected references, synthesize patterns across sources, or turn research into frameworks from curated reference collections (Are.na channels, bookmarks, saved articles).
This skill should be used to fix visual hierarchy when everything looks equally important, CTAs don't stand out, or users miss key information. Applies Von Restorff Effect, Serial Position Effect, and Law of Prägnanz.