Jev in production › Code and security review
Abide
Codifies AGENTS.md and CLAUDE.md rules into a JSON rubric that Jev checks against, catching rule violations static linters miss in coding agents.
- Use
- Code and security review
- Industry
- Developer tools
- Form
- Open-source tool
- Stage
- Beta
- Listed
- 2026-09-26
- Found via
- discord
- Repository
- coldteadotai/abide
- Stars
- 578
- Forks
- 45
- Last push
- 2026-10-10
- Language
- TypeScript
- License
- MIT
The README opens with
Coding agents break your rules from the very first edit. Abide catches every one and makes your agent fix it
1 in 13 turns break a rule no linter can catch · abide does · 300 ms per check · a tenth of a cent per turn Measured by replaying 93 real Claude Code sessions (1,256 edits, 147 turns) in two repos against their own AGENTS.md, for 22 cents. Jev flagged 39 edits and 15 turns; an independent reviewer confirmed 10 and 11. The turn-level catches (single-use abstractions, oversized files, duplicated logic) held up 11 times in 15. Method, per-rule table and what was wrong: benchmarks/replay .
Badge
For the project's own README, linking back here:
Also used for code and security review
- fingers (chainreactors) 1-2
- jgrep 92%
- JevGate $0.050
- Jevscan 56/60
- eslint-plugin-jev (ShahriarBijoy) ~100 ms
- jev-attack-surface-analysis about one cent per repo scanned
- JeVerifier 19-20 of 20
- prompt-fossils 460 of 617