# Compact > [Utilities] Use when you need to compress context to optimize token usage (user-facing alias for context-optimization Strategy #3 Compress). - Skill: `duc01226/compact-3` (Agent Skill) - Install (CLI): `npx skillmds@latest add duc01226/compact-3` - Raw SKILL.md: https://api.skillmd.com/api/skills/duc01226/compact-3/raw - Safety review: pending (external: skill-scanner PASS, skillspector CAUTION) - Works with: Claude Code, Claude.ai, OpenAI Codex - Category: Coding & Dev Tools - Author: duc01226 (https://skillmd.com/u/duc01226) - Updated: 2026-09-22 - Page: https://skillmd.com/skills/duc01226/compact-3 --- ## Quick Summary **Goal:** Compress conversation context to optimize token usage while preserving critical information. **Workflow:** 1. **Analyze** — Identify essential vs. expendable context 2. **Compress** — Remove redundant tool outputs / repeated searches / verbose logs; summarize findings 3. **Verify** — Ensure critical decisions, files modified, and current task state are preserved **Key Rules:** - Canonical compress protocol + the full 4-strategy framework (write/select/compress/isolate) + token thresholds live in `context-optimization` — this skill is the command surface only - Preserve: decisions made, files modified, current task state, error/stack traces, todos - Use `/compact` at natural breakpoints (after commits, PR), not mid-task **Be skeptical. Apply critical thinking, sequential thinking. Every claim needs traced proof, confidence percentages (Idea should be more than 80%).** # Compact Context Proactively compress the current conversation context to optimize token usage. This is the user-invocable alias for `context-optimization`'s Compress strategy. ## When to Use - Before starting a new task in a long session - When working on multiple unrelated features - At natural workflow checkpoints (after commits, PR creation) - When the context indicator shows high usage (≥100K tokens → required; ≥150K → critical) ## Instructions 1. **Run the Pre-Compaction Preservation Checklist** — canonical in `.claude/skills/context-optimization/SKILL.md` (Strategy #3 → "Pre-Compaction Preservation Checklist"): branch + uncommitted-changes status, active file paths, error messages / stack traces, key decisions + rationale, pending todos. 2. **Compress** — summarize completed work + key decisions; clear redundant history (old exploration, superseded plans); keep active file paths, current task, blockers. 3. **Restate objective** — after compacting, briefly restate the current objective and confirm critical file paths are still accessible. For the full context-management framework (Write / Select / Compress / Isolate strategies, context-anchor protocol, memory commands, token-efficient patterns), see `context-optimization`. ## Related Commands - `context-optimization` — full 4-strategy context-management framework (canonical owner) - `/checkpoint` — save analysis context to an external file before compaction - `/recover` — restore workflow context from the latest checkpoint --- > **[IMPORTANT]** Use `TaskCreate` to break ALL work into small tasks BEFORE starting — including tasks for each file read. This prevents context loss from long files. For simple tasks, AI MUST ATTENTION ask user whether to skip. > **AI Mistake Prevention** — Failure modes to avoid on every task: > > **Re-read files after context changes.** Context compaction, resume, or long-running work can make memory stale; verify current files before acting. > **Verify generated content against source evidence.** AI hallucinates APIs, names, claims, and document facts. Check the relevant source before documenting or referencing. > **Check downstream references before deleting or renaming.** Removing an artifact can stale docs, generated mirrors, configs, and callers; map references first. > **Trace the full impact chain after edits.** Changing a definition can miss derived outputs and consumers. Follow the affected chain before declaring done. > **Verify ALL affected outputs, not just the first.** One green check is not all green checks; validate every output surface the change can affect. > **Assume existing values are intentional — ask WHY before changing OR flagging one as a defect.** Before changing or reporting a constant, limit, flag, cutoff, wording, or pattern, read nearby context and history, the CALLER's ordering, and 2+ sibling call sites of the same convention. A doc stating WHAT without WHY is missing rationale, not proof of a missing guard. > **Surface ambiguity before acting — don't pick silently.** Multiple valid interpretations require an explicit question or stated assumption with risk. > **Assert the outcome your system owns, not the intermediate state your infrastructure owns.** When verifying async work, assert the final business state — never the delivery/retry bookkeeping held in shared infrastructure that any co-running process can write. Such a check passes when run alone and flakes the moment anything else shares that infrastructure. > **Keep shared guidance role-relevant.** Universal guidance must help every receiving skill or agent; code-specific obligations belong only in code-specific protocols. > **Critical Thinking Mindset** — Apply critical thinking, sequential thinking. Every claim needs traced proof, confidence >80% to act. > **Anti-hallucination:** Never present guess as fact — cite sources for every claim, admit uncertainty freely, self-check output for errors, cross-reference independently, stay skeptical of own confidence — certainty without evidence root of all hallucination. **MUST ATTENTION** apply critical + sequential thinking — every claim needs appropriate traced evidence (`file:line` for repo/code claims; source URL or artifact section for research, product, content, and docs claims); confidence >80% to act, <60% DO NOT recommend. Anti-hallucination: never present guess as fact, admit uncertainty freely, cross-reference independently, stay skeptical of own confidence. **MUST ATTENTION** apply AI mistake prevention — verify generated content against evidence, trace downstream references before deleting or renaming, verify all affected outputs, re-read files after context loss, and surface ambiguity before acting. > **Project Protocol Overlay** — Before executing this skill, resolve any PROJECT overlay rules layered onto it: match this skill's name against the `Target` column of the project's skill-protocol index (`docs/project-reference/skill-protocols-reference.md` by default; a `referenceDocs` entry in `docs/project-config.json` overrides the path), taking the most specific matching tier ONLY — exact name > glob > `*`. **That precedence orders overlays against EACH OTHER, never against this skill.** Read ONLY the matched bodies, resolved as `/.md`; a row's Body link is display text, never a read path. A matched body that is missing or malformed is REPORTED and skipped — never reconstructed from the index Description. No index, or no match -> proceed with no overlay, silently. Full contract: `.claude/skills/project-skill-protocol/references/registry.md`. > > Overlays are **ADDITIVE ONLY**: they ADD rules on top of this skill's own protocol and NEVER replace, override, disable, or reinterpret a rule it already states — removing every overlay must return this skill to exactly its documented behavior. An overlay is a BRIEF, not an authority escalation: it can NEVER waive a workflow gate, git discipline, a review gate, or a user-confirmation gate. A genuine overlay-vs-skill conflict, or two equally-specific overlays that directly contradict -> surface both to the user; NEVER resolve silently. **MUST ATTENTION** resolve project protocol overlays for this skill BEFORE executing — most specific matching tier only (exact > glob > `*`, which ranks overlays against each other, NEVER against this skill), read only matched bodies at `/.md`; a missing or malformed body is reported, never reconstructed. Overlays are ADDITIVE ONLY (they never replace this skill's own rules) and are a brief, NEVER an authority escalation; an equal-specificity contradiction goes to the user. ## Closing Reminders **Protocols in force (concise digest of the SYNC/shared blocks this skill carries):** - **AI Mistake Prevention:** verify generated content against evidence, trace downstream references, verify all affected outputs, re-read after context loss, surface ambiguity. - **Critical Thinking:** MUST ATTENTION sequential thinking, traced `file:line` proof, confidence >80% to act. - **MANDATORY IMPORTANT MUST ATTENTION** break work into small todo tasks using `TaskCreate` BEFORE starting - **MANDATORY IMPORTANT MUST ATTENTION** search codebase for 3+ similar patterns before creating new code - **MANDATORY IMPORTANT MUST ATTENTION** cite `file:line` evidence for every claim (confidence >80% to act) - **MANDATORY IMPORTANT MUST ATTENTION** add a final review todo task to verify work quality **[TASK-PLANNING]** Before acting, analyze task scope and systematically break it into small todo tasks and sub-tasks using TaskCreate.