AGENT SKILL

context-window-hygiene

Use when a conversation is getting long and the agent seems to be forgetting earlier instructions, before adding MCP servers or rules files, when deciding whether to clear or compact the chat, or when context window budget feels tight. Covers lost-in-the-middle, clear-vs-compact, and lean-context hygiene.

License 许可
MIT
最近更新
2026-11-15
Stars
★ 0
Forks
1

01 前言 Front Matter

name
context-window-hygiene
triggers
[ "user", "model" ]
description
Use when a conversation is getting long and the agent seems to be forgetting earlier instructions, before adding MCP servers or rules files, when deciding whether to clear or compact the chat, or when context window budget feels tight. Covers lost-in-the-middle, clear-vs-compact, and lean-context hygiene.

03 SKILL.md 正文

Context Window Hygiene

Core Facts

  • Context window = input + output tokens the model sees at once. Every system prompt, rules file, MCP tool definition, message, and tool result counts against a hard limit set by the model provider.
  • Hard limit. Each model has a fixed token ceiling (e.g. 200k, 2M). Hit it and the provider errors, or output stops mid-generation.
  • Smart zone vs dumb zone. AI-coding workflow guides observe that output quality drops once the active context passes roughly ~100k tokens, regardless of the model's total window. Stay in the smart zone by sizing tasks so the working context stays well below that marker.
  • Bigger window ≠ better retrieval. A 10M-token window that cannot find the needle is worse than a 200k window that can. Evaluate retrieval quality, not just size. (Llama 4 Scout: 10M window, severe lost-in-the-middle.)
  • Lost in the middle. In long contexts the attention mechanism deprioritizes information in the middle of the conversation. Start (primacy) and end (recency) dominate. Middle detail has weak impact.

When to Use

  • Conversation is long and the agent is drifting or ignoring early rules.
  • Deciding whether to clear or compact.
  • About to add an MCP server, a large rules file, or paste a huge document.
  • Choosing a model by context size.

When NOT to Use

  • Context is small and focused - direct work is cheaper.
  • You need dense access to early detail - use context-folding instead.

Clear vs Compact

Action What it does When
clear Wipes history, blank slate Default. Task is done or unrelated to prior chat.
compact Summarizes history into a small message Preserve the vibes/intent of the current task while freeing space. Costs tokens + time to generate the summary.

Default to clear. Use compact only when continuing the same task and losing the thread would hurt. Compaction drops detail - it preserves intent, not facts. If dense access to early context is needed, use context-folding (offload to file, grep/read on demand) instead of compacting.

Critique of compaction: summaries leave "sediment" (lossy residue that still occupies attention) and are a worse default than a clean /clear once the session enters the dumb zone. Treat /compact as an escape hatch, not a hygiene default.

Lean Context Rules

  1. Clear chats between unrelated tasks. Refreshes memory, removes lost-in-the-middle noise. A fresh thread outperforms a bloated one.
  2. Keep rules files small. .devin/global_rules.md / .devin/rules/*.md / cursor rules / claude rules are loaded into every conversation. A 25k-token rules file is 12% of a 200k window before you say a word. Compress, modularize into skills, reference instead of inlining. See writing-for-agents.
  3. Be paranoid about MCP servers. Each server injects every tool definition into the system prompt. Two servers can eat a third of the window before the first message. Audit before adding - use mcp-context-audit. Keep tool count per server under 10-15.
  4. Don't paste huge documents into chat. Write to a file with write, then read with offset/limit or grep to pull only what's needed. This is context-folding at its simplest.
  5. Prefer subagents for parallel exploration. Each subagent has its own window; only the synthesis returns to the root. 50-100x context savings. See dispatching-parallel-agents.
  6. Watch the budget. Run context-budget.py (SessionStart hook) to see the token cost of .devin/global_rules.md + loaded rules before working.
  7. Guard against context overflow. If a tokens-limit or equivalent guard is available, use it. If the active context approaches the threshold, stop the current task, clear or compact, and restart with a leaner context. Loops without a bound are a cost and correctness risk.

Anti-Patterns

  • Keeping one long chat for the whole day. Maximizes lost-in-the-middle.
  • Adding MCP servers "just in case." Permanent context tax for unused tools.
  • Writing giant rules files. Self-defeating: the rules degrade retrieval of everything else in context.
  • Pasting a 500k log into chat. Use a file + grep.
  • Compacting when you need the original detail. Compaction is lossy.
  • Running unbounded loops. Every iteration burns tokens; cap retries and stop when the context threshold is reached.

Model Selection Heuristic

Need Pick
Long chat, simple retrieval Large window with good needle-in-haystack benchmarks
Precision on early rules Smaller window, clear often
Huge document analysis context-folding on any model; don't rely on window size alone

Source

Distilled from AI-coding workflow guides on context-window hygiene and compaction trade-offs.

Key claims verified against primary sources:

  • Lost-in-the-middle: Liu et al. (arXiv:2307.03172).
  • Window limits are provider-set and hard: models.dev model cards.
  • Compaction is lossy by design: see context-folding comparison table.

If the user asks for current context-window limits or model benchmarks, invoke research to fetch the latest model cards and papers.

04 同仓库更多 Skills

Leostruka
Leostruka/devin-bundle

montador-de-ideias

Use when assembling, expanding, or elevating a raw project idea or initial prompt into an ultra-detailed, first-principles dossier and compiled master prompt with journalistic OSINT market research, Tech Lead and Staff Architect justifications, atomic and modular hardening/optimization, and high-impact contact surfaces.

★ 0
Leostruka
Leostruka/devin-bundle

git-github-adaptive-engineering

Use when any task touches git history, GitHub issues/PRs/releases/CI, repo governance, or branch and merge decisions. Runs the Fase Zero situational-awareness battery, picks one of five delivery flows via the adaptive decision engine, and enforces commit/PR information-density standards. Orchestrates the gh, git-workflows, github-actions, pr, and debug/finish skills.

★ 0
Leostruka
Leostruka/devin-bundle

adaptive-agenda-calendar-routine-engine

Use when planning or executing work across hours, days, weeks, or sprints. Turns the calendar into a strict time-blocked agenda (HH:MM-HH:MM blocks carrying a routine profile, expected inputs, and a handoff output artifact), runs the 5-stage cognitive flow (Radar and Hunt -> Triage plus Steve Jobs conception -> workbench manifest -> >=32-cycle loop -> Close plus Open-Minded Scrum), and unfolds macro calendar milestones into micro agenda blocks through extensions/gcal/wrapper.py.

★ 0
Leostruka
Leostruka/devin-bundle

demo

Use when demonstrating a skill in a fixture project.

★ 0
Leostruka
Leostruka/devin-bundle

duplicate-skill

Use when testing duplicate skill name detection.

★ 0
Leostruka
Leostruka/devin-bundle

duplicate-skill

Use when testing duplicate skill name detection.

★ 0