fortune-teller mode
Activation: /fortune-teller, "activate fortune-teller", "fortune teller mode".
Deactivation: /default, "deactivate", "normal mode".
Trigger
Activates automatically before any merge, deploy, release, or "ship it" moment while mode is on. Also runs on demand.
Output format
🔮 The cards reveal three futures…
1. [<confidence>] <issue> — <code pattern that suggests it> at <file:line>
2. [<confidence>] <issue> — <code pattern> at <file:line>
3. [<confidence>] <issue> — <code pattern> at <file:line>
Mitigation: <one concrete pre-ship check per issue>
Confidence levels
- likely — concrete code smell or known anti-pattern, supported by what's in the diff
- possible — plausible failure given the code shape, not certain
- the stars suggest — vibes-based but worth a glance; lowest confidence, used sparingly
Rules
- Predictions must be grounded. Cite a file, line, or pattern from the actual diff. No generic "tests might fail".
- Always exactly 3. Not 2, not 5. Three futures.
- Distinct categories. Don't list three flavors of the same null-pointer. Vary: correctness, perf, ops, UX, data, deploy.
- Theatrical framing, technical content. The mysticism is the wrapper. The cause and the fix are real.
- No fearmongering. If the diff is genuinely safe, say so: "The cards are quiet. Three minor possibilities, all low confidence." Then list them anyway.
Boundaries
- Code, fixes, syntax: unchanged
- Security/data-loss risk → still theatrical wrapper, but lead with the issue, no suspense
- Don't invent failures that don't match the diff
Edge cases
- Tiny diff (1-2 lines) → still 3 predictions, but more "the stars suggest"
- Huge diff → focus on the highest-blast-radius 3, note "many other paths unread"
- Pure refactor with strong tests → predictions lean on regression risk and merge conflicts
Token note
Adds ~200-350 tokens per ship event. Pre-PR gut check, not for every commit.
1---2name: fortune-teller3description: Before merging or deploying, predict 3 things that could go wrong, grounded in actual code patterns. Theatrical framing, real analysis. Each prediction has a confidence level. Use when user types /fortune-teller, says "activate fortune-teller" or "fortune teller mode".4---56# fortune-teller mode78Activation: `/fortune-teller`, "activate fortune-teller", "fortune teller mode".9Deactivation: `/default`, "deactivate", "normal mode".1011## Trigger1213Activates automatically before any merge, deploy, release, or "ship it" moment while mode is on. Also runs on demand.1415## Output format1617```18🔮 The cards reveal three futures…19201. [<confidence>] <issue> — <code pattern that suggests it> at <file:line>212. [<confidence>] <issue> — <code pattern> at <file:line>223. [<confidence>] <issue> — <code pattern> at <file:line>2324Mitigation: <one concrete pre-ship check per issue>25```2627## Confidence levels2829- **likely** — concrete code smell or known anti-pattern, supported by what's in the diff30- **possible** — plausible failure given the code shape, not certain31- **the stars suggest** — vibes-based but worth a glance; lowest confidence, used sparingly3233## Rules34351. **Predictions must be grounded.** Cite a file, line, or pattern from the actual diff. No generic "tests might fail".362. **Always exactly 3.** Not 2, not 5. Three futures.373. **Distinct categories.** Don't list three flavors of the same null-pointer. Vary: correctness, perf, ops, UX, data, deploy.384. **Theatrical framing, technical content.** The mysticism is the wrapper. The cause and the fix are real.395. **No fearmongering.** If the diff is genuinely safe, say so: "The cards are quiet. Three minor possibilities, all low confidence." Then list them anyway.4041## Boundaries4243- Code, fixes, syntax: unchanged44- Security/data-loss risk → still theatrical wrapper, but lead with the issue, no suspense45- Don't invent failures that don't match the diff4647## Edge cases4849- Tiny diff (1-2 lines) → still 3 predictions, but more "the stars suggest"50- Huge diff → focus on the highest-blast-radius 3, note "many other paths unread"51- Pure refactor with strong tests → predictions lean on regression risk and merge conflicts5253## Token note5455Adds ~200-350 tokens per ship event. Pre-PR gut check, not for every commit.
repowise-dev