Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Get Started Free →

Behavior Contract: [Bug Title] — measured AI agent skill | DecimalAI

a5c-ai/behavior-contract

SkillScore95Maintained

Bug condition/postcondition formalization as testable Behavior Contracts. Defines invariants that must be preserved across fixes.

by a5c-ai

Links this skill to your agents and keeps it current with the author’s updates.

Automatic

QA & Test Engineering pack

decimalai skills pull a5c-ai-behavior-contract

Get this skill — curl · raw file

curl -fsSL https://app.decimal.ai/s/a5c-ai-behavior-contract/SKILL.md

Raw file: /s/a5c-ai-behavior-contract/SKILL.md ↗ · machine-readable summary at /s/a5c-ai-behavior-contract.json ↗

In productionGlobal

how this skill behaves on real traffic · last 30 days

No production data for this skill yet — usage numbers appear here once agents start running it.

Anonymized aggregate across every org using this skill — proof from real production use, not a demo.

Does this skill help? · Benchmark: with vs. withoutsign in to run this on your agents

22 test cases from the publisher’s eval.yaml · each run twice on gemini-3.6-flash — with the skill injected, then without · last run 7d ago

Yes — +64% lift-48% tokens0% turns95% of whole cases pass with skill (21/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-01	✗→✓	▲ Improved	-52%	0%
case-02	✗→✓	▲ Improved	-61%	0%
case-03	✗→✓	▲ Improved	-52%	0%
case-04	✗→✓	▲ Improved	-64%	0%
case-05	✗→✓	▲ Improved	-36%	0%

Showing 5 of 22 cases

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 7/31/2026

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

a5c-ai / babysitter

library/methodologies/pilot-shell/skills/behavior-contract/SKILL.md

View on GitHub ↗

License MITImported 7/31/2026Version v1

Skill contents

SKILL.md

"Positive amounts still process correctly"
"Negative amounts still throw InvalidAmountError"
"Receipt format remains unchanged for all amount types"

Contract Document Template

markdown
# Behavior Contract: [Bug Title]

## Bug Condition
[Precise description of triggering conditions]

## Postcondition
[Expected correct behavior after fix]

## Invariants
- [ ] Invariant 1: [existing behavior to preserve]
- [ ] Invariant 2: [existing behavior to preserve]

## Testable Assertions
1. `expect(processPayment(0)).toEqual({ amount: 0, status: 'completed' })`
2. `expect(processPayment(100)).toEqual({ amount: 100, status: 'completed' })`
3. `expect(() => processPayment(-1)).toThrow(InvalidAmountError)`

Usage in Bugfix Workflow

Bug analysis identifies root cause at file:line
This skill formalizes the contract from the analysis
tdd-enforcer writes failing test from Bug Condition
tdd-enforcer writes preservation tests from Invariants
Minimal fix applied, contract audited

Want to see if a5c-ai/behavior-contract would activate on your phrasing? Try it before you install — no LLM call, no signup.

Other measured skills in the registry, with their headline benchmark lift.