context-mode
Skill1 starsChanged 5 months agoMITView on GitHub
Manage context windows efficiently — summarize, compress, and preserve critical information across sessions
7 other projects use a version of this.
Adopted by
Most recently taken up by
- AthenDrakomin-hub/agent-skillstheir own version, first seen Nov 1, 2026
- pedroiff0/awesome-skillstheir own version, first seen Sep 29, 2026
- opencue/cuecardstheir own version, first seen Aug 17, 2026
- williamcorrea23/sap-router-skilltheir own version, first seen Jul 13, 2026
- javimosch/superclitheir own version, first seen Jun 3, 2026
- iltutishrak/claude-skillstheir own version, first seen May 26, 2026
Other versions7 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 7
- javimosch/supercli★ 53same name
- opencue/cuecards★ 6same name
- pedroiff0/awesome-skills★ 1same name
- williamcorrea23/sap-router-skill★ 1same name
- AthenDrakomin-hub/agent-skills★ 0same name
- iltutishrak/claude-skills★ 0same name
- yusuf787x/claude-skills★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository84 other files it gives its agents.
- api-design-reviewerSkill
- api-test-suite-builderSkill
- ask-mattSkill
- aws-solution-architectSkill
- captureSkill
- changelog-generatorSkill
- ci-cd-pipeline-builderSkill
- cloud-securitySkill
- codebase-designSkill
- codebase-onboardingSkill
- code-reviewerSkill
- context-compressSkill
- database-designerSkill
- database-schema-designerSkill
- dependency-auditorSkill
- diagnosing-bugsSkill
- domain-modelingSkill
- env-secrets-managerSkill
- finish-branchSkill
- firecrawlSkill
- focused-fixSkill
- frontend-designSkill
- get-shit-doneSkill
- git-guardrails-claude-codeSkill
- git-worktree-managerSkill
- git-worktreesSkill
- grillingSkill
- grill-meSkill
- grill-with-docsSkill
- handoffSkill
- implementSkill
- improve-codebase-architectureSkill
- incident-commanderSkill
- incident-responseSkill
- mcp-builderSkill
- memSkill
- migration-architectSkill
- monorepo-navigatorSkill
- observability-designerSkill
- performance-profilerSkill
- playwright-testingSkill
- ponytail-auditSkill
- ponytail-debtSkill
- ponytail-gainSkill
- ponytail-helpSkill
- ponytail-reviewSkill
- ponytailSkill
- prompt-engineeringSkill
- prototypeSkill
- pr-review-expertSkill
- rag-architectSkill
- red-teamSkill
- reflectSkill
- resolving-merge-conflictsSkill
- root-cause-tracingSkill
- runbook-generatorSkill
- self-evalSkill
- senior-architectSkill
- senior-backendSkill
- senior-devopsSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
7 rules. 0 are common, 5 are distinctive, and 2 are very specific to this project.
0
Common
Most of the 6 edited versions we read keep these.
5
Distinctive
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 59
Use notes.md for cross-session observations
- Distinctive: line 61
Search memory before re-exploring
- Distinctive: line 68
Don't pass full conversation to every subagent
- Distinctive: line 89
Rule of thumb: If you're reading it twice, summarize it once.
- Distinctive: line 93
When context is tight:
- Very specific: line 95
Write findings to notes.md or task progress
- Distinctive: line 98
Start fresh session with focused prompt
“Common” is measured: kept by at least 6 in 10 of the 6 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Context Mode
Optimize context usage. Keep what matters, compress what doesn't, preserve across sessions.
When to Use
- Context window getting full
- Starting a new session with prior work
- Need to preserve decisions across checkpoints
- Large codebase exploration consuming tokens
Context Management Strategies
1. Summarize Aggressively
Replace verbose output with concise summaries:
Bad: Full stack trace with 50 lines
Good: "TypeError at src/api.ts:42 — missing null check on response.data.user"
Bad: Entire file content read
Good: "File has 200 lines, key function at line 85-120, uses X pattern"
Bad: Running every test individually
Good: "All 47 tests pass, coverage at 82%"2. Layer Information
Organize context by relevance:
Critical (always keep):
- Current task goal
- Active blockers
- Key architectural decisions
- File paths of modified files
Important (summarize when needed):
- Prior conversation decisions
- Test results
- Code exploration findings
Ephemeral (drop when context tight):
- Full file contents (re-read on demand)
- Verbose command output
- Intermediate search results3. Use Memory System
- Store durable facts in
MEMORY.md - Use
notes.mdfor cross-session observations - Reference memory instead of re-deriving
- Search memory before re-exploring
4. Parallel Context via Subagents
- Spawn subagents for heavy exploration
- Each subagent gets clean context
- Synthesize findings, not raw output
- Don't pass full conversation to every subagent
Checkpoint Discipline
At checkpoint time, ensure these are captured:
- What was accomplished (not what was attempted)
- Key decisions and their rationale
- Current state of modified files
- Blockers and how to resolve them
- Next action (specific, not vague)
Token Budget Awareness
| Content | Approximate Cost |
| Full file read (500 lines) | ~2000 tokens |
| Command output (100 lines) | ~400 tokens |
| Subagent prompt | ~500 tokens |
| Checkpoint summary | ~800 tokens |
Rule of thumb: If you're reading it twice, summarize it once.
Session Handoff
When context is tight:
- Write findings to
notes.mdor task progress - Summarize what's done and what's next
- Reference specific file paths and line numbers
- Start fresh session with focused prompt
Anti-Patterns
| Pattern | Problem |
| Reading full files unnecessarily | Burns tokens |
| Re-deriving from memory | Wastes context |
| Passing full conversation to subagents | Redundant context |
| Keeping verbose command output | Noisy, hard to parse |
| Not summarizing at checkpoints | Loses critical info |
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

