Automated README summary
Automatically summarized from the README on 29 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
A four-hook defense matrix for Claude Code that scans project instructions, gates tool calls, detects indirect prompt injection, and audits task completion, aimed at developers running long autonomous coding agents.
How it uses Jev
On each tool call, Jev scores eight typed dimensions (destructive, exfiltration, sensitive_target, impact, policy_allows, user_requested, self_advocating, from_untrusted) from tool name, arguments, and workspace state; thresholds map scores to allow, ask, or deny. PostToolUse and Stop hooks use Jev to classify injection and completion issues.
Primitives:choicescorenoul
Technique worth stealing
Reasoning-blind gating: send only tool name, arguments, and recent state to a fast typed model, never the agent's chain-of-thought.
Try it
Clone the repo, copy hooks/*.py to ~/.claude/hooks/, register hooks in ~/.claude/settings.json, then run python3 tests/test_gate_security.py.
Model judgments from README excerpts
Project signals use repository metadata, an existing summary and the first 700 README characters, not the full project. “Not found” means not detected in that material; it does not establish absence. These are the original judgments with recorded models and dates, not source audits or run results.
Models & evaluation dates
- Inclusion gate
jev-1.14.0- Project signals
jev-1.14.0- Category
jev-1.14.0- Pattern tags
jev-1.14.0
Evidence
These signals use repository metadata, an existing summary and at most 700 cleaned README characters. ≥ 0.60 means reported in that excerpt; ≤ 0.40 means not found there. The middle band is inconclusive. None is a source-code audit or a test result. The runnable-tool question excludes research experiments; the recommendation question asks for a learning shortlist, not a quality verdict.
- Jev is core to the projectFound in material0.86
- Shows a System One patternunclear0.57
- Describes handling uncertaintynot found in the excerpt0.07
- Reports measured numbersnot found in the excerpt0.09
- Is a runnable toolFound in material0.83
- Top-10 learning shortlist signalnot found in the excerpt0.16
- Is a replica of the modelnot found in the excerpt0.13
- Solves a common problem (0–2)score on a 0–2 scale1.35 / 2
- About JevFound in material0.97
no-judgment band (0.40–0.60)
no-judgment band (0.40–0.60)
The Jev model and date for each judgment stage are listed above. Card written by DeepSeek V4.1 Flash from the README on 29 Oct 2026.