메뉴
Audit what auto-loads into an agent session's context window and suggest lean, reversible fixes to cut startup tokens.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Audit the current project's agent-memory and, block by block, relocate each entry into a user-controlled home (project doc/skill/rule or user-level skill/rule) or archive it — draining memory so nothing uncontrolled accumulates in the agent's context.
How to write texts meant to be published by humans for other humans.
Fresh-eyes review of a changeset by a fresh-context agent — catches regressions and correctness issues the authoring context reads past.
Check how much of a ticket is already implemented — split it into requirement blocks, judge each against the code, and save a human-readable TICKET-STATUS report in the planning dir.
Author or refine a skill for maximum token economy without losing intent. Use when creating any new skill or editing an existing `SKILL.md`.
Assist a human reviewing a pull request or branch locally — diff a source branch against its target (auto-detected or from a PR link) and return concise, human-voice review comments with file and line locations. Read-only, never posts.
| name | context-checkup |
| description | Audit what auto-loads into an agent session's context window and suggest lean, reversible fixes to cut startup tokens. |
| disable-model-invocation | true |
| type | flow |
| license | MIT |
| metadata | {"author":"Francesco Borzì","version":"1.2"} |
Find what loads automatically into the session's context at startup, quantify it, and propose reversible trims ranked by payoff — shrink the startup context window by cutting what isn't worth its tokens. Read-only — measure and recommend; change settings only on explicit approval.
Cost hierarchy, biggest first:
@imports, and skill/agent/command
descriptions (every available one's description loads every session).Rules: measure, never guess — wc/count, then attach a rough token figure to each finding.
Rank by tokens-saved × reversibility. Distinguish auto-loaded from lazy-linked (nested
AGENTS.md referenced from a parent are not loaded — don't flag them).
Tool-name counts, the skills/agents/commands lists, and tool-search status come from the session's system-reminders, not disk — read them from your own context.
0. Verify tool search is on first. If ENABLE_TOOL_SEARCH is disabled, MCP schemas load eagerly
and every "names are cheap" conclusion flips. Check this before anything else.
1. Always-on docs. Measure the CLAUDE.md/AGENTS.md chain: project file + every parent dir up
to root + global ~/.claude/CLAUDE.md. Expand @import lines (recursive). wc -w each.
2. Descriptions (often the largest unexamined chunk). Skim the in-session lists of skills, subagent types, and slash commands — their descriptions are always loaded. Many rarely-used entries = standing cost.
3. MCP servers. From .mcp.json + settings, list enabled servers. Count tool names per
server; note any server with long instructions. Flag servers irrelevant to the user's work.
4. Enablement levers. Read ~/.claude/settings.json, project .claude/settings.json,
.claude/settings.local.json. Check enableAllProjectMcpServers, enabledMcpjsonServers,
enabledPlugins. Precedence: managed > local > project > user. Each plugin can pull in MCP servers,
skills, agents, hooks.
5. Memory. Size of MEMORY.md index.
A short sizes table (source → ≈ tokens → auto-loaded? → relevant to user's work?), then a prioritized action list. For each action give the exact setting/file edit, the rough savings, and how to reverse it (prefer per-session toggles). Skip anything under ~a few hundred tokens unless asked to be exhaustive. Then ask before editing.
# always-on doc chain (run from project root; also check parent dirs + ~/.claude/CLAUDE.md)
for f in CLAUDE.md AGENTS.md ../CLAUDE.md ~/.claude/CLAUDE.md; do [ -f "$f" ] && wc -w "$f"; done
# enabled MCP + settings
cat .mcp.json; cat .claude/settings.json .claude/settings.local.json ~/.claude/settings.json 2>/dev/null