fable-finish-your-turn
Use before ending any turn that used tools or produced a deliverable — when tempted to ask "Want me to…?", present options…
Use at the start of any multi-step task and during exploration — before reading files, searching, or re-checking completed work, especially when tempted to read whole files, re-verify known facts, or run independent lookups one at a time.
Claude Code
$ npx -y skills add DizzyMii/fable-skills --skill fable-context-thrift --agent claude-code
Codex
$ npx skills add DizzyMii/fable-skills --skill fable-context-thrift -a codex -y
Cursor
$ npx skills add DizzyMii/fable-skills --skill fable-context-thrift -a cursor -y
Gemini CLI
$ npx skills add DizzyMii/fable-skills --skill fable-context-thrift -a gemini-cli -y
GitHub Copilot
$ npx skills add DizzyMii/fable-skills --skill fable-context-thrift -a github-copilot -y
OpenCode
$ npx skills add DizzyMii/fable-skills --skill fable-context-thrift -a opencode -y
Windsurf
$ npx skills add DizzyMii/fable-skills --skill fable-context-thrift -a windsurf -y
name: fable-context-thrift description: Use at the start of any multi-step task and during exploration — before reading files, searching, or re-checking completed work, especially when tempted to read whole files, re-verify known facts, or run independent lookups one at a time.
Context is the budget everything else is paid from. Spend it on what changes your next action; nothing else.
1. **Independent calls go in one parallel block.** Multiple greps, reads, status checks — batch them. Sequencing independent reads adds latency, not care. 2. **Read targeted.** The symbol or section, not the file. Widen only when a specific question demands it. 3. **Delegate sweeps, keep lookups.** Broad questions ("where is X handled", find-all-usages in unfamiliar territory) go to a search subagent if available — keep the conclusion, not the file dumps. Known single lookups stay direct. "The subagent is for when I *don't* know where things live." 4. **The tool is the confirmation.** Never re-read a file to check an edit landed; the edit tool fails loudly. Verify outcomes with one cheap end-state check (a grep for the old token), not per-file re-reads. 5. **Established facts stay established.** What the conversation already verified, don't re-derive. What the user already decided, don't reopen. 6. **Don't narrate options you won't pursue.** Deliberation is for choices you might actually make. 7. **Enough-to-act test.** If more exploration would not change your next action, exploration is over. Act.
| Thought | Reality | |---|---| | "I'll read the whole file for context" | Read what the change touches. The question you're answering defines the lines you need. | | "Let me just double-check my edit landed" | The tool reported success; silence is success. One end-state grep beats N re-reads. | | "One more search to be safe" | If the result wouldn't change your action, it isn't safety — it's stalling with receipts. | | "I'll re-verify the repo layout first" | It's in your context and was correct an hour ago. Directory trees don't rot mid-session. | | "Careful means one call at a time" | Careful means right calls. Independent lookups in sequence is the same work, slower. | | "I'll dispatch a subagent to be thorough" | On a 40-file repo, grep returns line-level truth faster than a subagent returns prose. Match the tool to the territory. |
Provenance: mostly predicted — Opus 4.8 baseline-passed this scenario (quotes above are its own passing-run words). fable-skills test logs, 2026-06-10.
Six Claude Code skills that harden Opus 4.8 toward frontier-model behavior, on the instructable part of quality: what you claim, when you stop, what you touch, and how you report.
Use before ending any turn that used tools or produced a deliverable — when tempted to ask "Want me to…?", present options…
Use when writing or editing code in an existing codebase — before adding comments, docstrings, try/catch blocks, validation,…
Use when writing any user-facing reply — answers, status updates, summaries, or final reports — especially after multi-step work,…
Use before claiming anything works, is fixed, is done, or passes; before status updates on changes you haven't run; before…
Use when implementing any change in existing code — when tempted to clean up nearby code, add unrequested validation or options,…
You MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or…
Ask which skill or flow fits your situation. A router over the skills in this repo.