Skills › Superpowers › writing-skills › bulletproofing.md

bulletproofing.md

80 lines · skills/writing-skills/references/bulletproofing.md at 2ce8aa1

1# Bulletproofing Skills Against Rationalization

3Part of superpowers:writing-skills. Use it when the baseline failure is a

4discipline failure: the agent knows the rule and skips it under pressure.

Bulletproofing Skills Against Rationalization

Part of superpowers:writing-skills. Use it when the baseline failure is a discipline failure: the agent knows the rule and skips it under pressure.

Raw lines 1 to 5

6## Bulletproofing Skills Against Rationalization

8Skills that enforce discipline (like TDD) need to resist rationalization. Agents are smart and will find loopholes when under pressure.

10**Scope:** this toolkit is for discipline failures — an agent that knows the rule and skips it under pressure. For wrong-shaped output or omitted elements, prohibition-based bulletproofing backfires; use the forms in Match the Form to the Failure instead.

12**Psychology note:** Understanding WHY persuasion techniques work helps you apply them systematically. See persuasion-principles.md in this directory for research foundation (Cialdini, 2021; Meincke et al., 2025) on authority, commitment, scarcity, social proof, and unity principles.

Bulletproofing Skills Against Rationalization

Skills that enforce discipline (like TDD) need to resist rationalization. Agents are smart and will find loopholes when under pressure.

Scope: this toolkit is for discipline failures — an agent that knows the rule and skips it under pressure. For wrong-shaped output or omitted elements, prohibition-based bulletproofing backfires; use the forms in Match the Form to the Failure instead.

Psychology note: Understanding WHY persuasion techniques work helps you apply them systematically. See persuasion-principles.md in this directory for research foundation (Cialdini, 2021; Meincke et al., 2025) on authority, commitment, scarcity, social proof, and unity principles.

Raw lines 6 to 13

14### Close Every Loophole Explicitly

16Don't just state the rule - forbid specific workarounds:

18<Bad>

19```markdown

20Write code before test? Delete it.

21```

22</Bad>

24<Good>

25```markdown

26Write code before test? Delete it. Start over.

28**No exceptions:**

29- Don't keep it as "reference"

30- Don't "adapt" it while writing tests

31- Don't look at it

32- Delete means delete

33```

34</Good>

Close Every Loophole Explicitly

Don't just state the rule - forbid specific workarounds:

<Bad>

Write code before test? Delete it.

</Bad>

<Good>

Write code before test? Delete it. Start over.

**No exceptions:**
- Don't keep it as "reference"
- Don't "adapt" it while writing tests
- Don't look at it
- Delete means delete

</Good>

Raw lines 14 to 35

36### Address "Spirit vs Letter" Arguments

38Add foundational principle early:

40```markdown

41**Violating the letter of the rules is violating the spirit of the rules.**

42```

44This cuts off entire class of "I'm following the spirit" rationalizations.

Address "Spirit vs Letter" Arguments

Add foundational principle early:

**Violating the letter of the rules is violating the spirit of the rules.**

This cuts off entire class of "I'm following the spirit" rationalizations.

Raw lines 36 to 45

46### Build Rationalization Table

48Capture rationalizations from baseline testing (see Testing section below). Every excuse agents make goes in the table:

50```markdown

51| Excuse | Reality |

52|--------|---------|

53| "Too simple to test" | Simple code breaks. Test takes 30 seconds. |

54| "I'll test after" | Tests passing immediately prove nothing. |

55| "Tests after achieve same goals" | Tests-after = "what does this do?" Tests-first = "what should this do?" |

56```

Build Rationalization Table

Capture rationalizations from baseline testing (see Testing section below). Every excuse agents make goes in the table:

| Excuse | Reality |
|--------|---------|
| "Too simple to test" | Simple code breaks. Test takes 30 seconds. |
| "I'll test after" | Tests passing immediately prove nothing. |
| "Tests after achieve same goals" | Tests-after = "what does this do?" Tests-first = "what should this do?" |

Raw lines 46 to 57

58### Create Red Flags List

60Make it easy for agents to self-check when rationalizing:

62```markdown

63## Red Flags - STOP and Start Over

65- Code before test

66- "I already manually tested it"

67- "Tests after achieve the same purpose"

68- "It's about spirit not ritual"

69- "This is different because..."

71**All of these mean: Delete code. Start over with TDD.**

72```

Create Red Flags List

Make it easy for agents to self-check when rationalizing:

## Red Flags - STOP and Start Over

- Code before test
- "I already manually tested it"
- "Tests after achieve the same purpose"
- "It's about spirit not ritual"
- "This is different because..."

**All of these mean: Delete code. Start over with TDD.**

Raw lines 58 to 73

74### Update SDO for Violation Symptoms

76Add to description: symptoms of when you're ABOUT to violate the rule:

78```yaml

79description: use when implementing any feature or bugfix, before writing implementation code

80```

Update SDO for Violation Symptoms

Add to description: symptoms of when you're ABOUT to violate the rule:

description: use when implementing any feature or bugfix, before writing implementation code

Raw lines 74 to 80