Borrowing it
Nothing to install: this file belongs to shino369/claude-code-personal-workspace. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/shino369/claude-code-personal-workspace/main/.claude/skills/context-manager/SKILL.mdgit clone --depth 1 https://github.com/shino369/claude-code-personal-workspaceWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/shino369/claude-code-personal-workspace/context-manager)<a href="https://agentmods.dev/skills/shino369/claude-code-personal-workspace/context-manager"><img src="https://agentmods.dev/badge/skills/shino369/claude-code-personal-workspace/context-manager/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/shino369/claude-code-personal-workspace/context-manager"><img src="https://agentmods.dev/badge/skills/shino369/claude-code-personal-workspace/context-manager.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00037 | $0.01766 |
| Opus 5.5 | $0.00015 | $0.00706 |
| Sonnet 5.5 | $0.00007 | $0.00353 |
| Haiku 4.5 | $0.00004 | $0.00177 |
Grade A, and why
context-manager scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 220 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Context Management for Optimal Performance
Context quality degrades at 20-40% usage, so manage it before the window fills. The actual window depends on the model (1M tokens by default in this workspace); set CLAUDE_CONTEXT_WINDOW if you run a different window size.
A UserPromptSubmit hook (.claude/hooks/context_monitor.js) measures real usage from the transcript and injects [Context Monitor] warnings at 20%, 40%, and 60%. Use this skill when one of those warnings appears.
Why Context Management Matters
The degradation pattern:
- 0-20%: Optimal performance
- 20-40%: Quality starts to chip away (subtle but present)
- 40-60%: Noticeable degradation begins
- 60%+: Significant quality loss, even after compaction
Compaction doesn't restore quality - It only buys a bit more space. If quality was already degraded before compaction, it stays degraded after.
Symptoms of Context Degradation
Watch for these signs:
- Repetition - Explaining the same thing 3+ times without progress
- Loops - Trying same solution repeatedly, failing each time
- Confusion - Mixing up different parts of codebase
- Missed context - Forgetting information from earlier in conversation
- Overengineering - Adding unnecessary abstractions unprompted
- Off-target - Implementations that miss the actual requirements
If you notice any of these, context is likely degraded. Time to intervene.
Prevention Strategies
1. Scope Conversations Per Feature
Do: One conversation per task/feature
✅ Conversation 1: Build authentication system
✅ Conversation 2: Refactor database queries
✅ Conversation 3: Add user profile page
Don't: Mix unrelated tasks in same conversation
❌ Conversation 1: Build auth + refactor DB + add profile + fix bug in checkout
Why: Contexts bleed together. Claude gets confused about which patterns apply where.
2. Use External Memory Files
Write plans and progress to files that persist across sessions:
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 10d ago First seen · 220 lines · 37 tokens per session scan A f31fc8e8578a
context-manager is a skill published in the GitHub repository shino369/claude-code-personal-workspace (3 stars, last pushed 11d ago), licensed ISC. It adds 37 tokens to every session and 1,766 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-18.
Other skills, from other repositories
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
agentmail
Use your assigned AgentMail inbox to read email tasks, explicitly send or reply, and check delivery. Provided automatically by your inbox assignment.
Cortex
LifeOS memory, prior-session recall, and learning capture. USE WHEN capture this learning, document this learning, what did we learn recently, recent learnings, cortex, knowledge, knowledge base, search knowledge, what do we know about, archive, harvest, knowledge status, develop note, add to knowledge, add a people…
rowboat-spaces
How to work as a member of Rowboat Spaces, the team chat where people and agents work together. Load it once per session, before acting on any request that reaches you from Rowboat; it covers your setup, mentions and hand-offs, the tools, and files.
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.