Automated README summary
Automatically summarized from the README on 1 Nov 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
toolgate gates AI agent tool calls before they run, returning allow, ask, or deny. It ships as a Claude Code mod or hook, an OpenCode plugin, and an MCP proxy for Cursor, Claude Desktop, and custom agents.
How it uses Jev
Before a risky tool call, toolgate sends Jev seven questions (destructive, exfiltration, privilege, secret_exposure, off_task, violates_constraint, unresolved_choice) plus the mitigator authorized, with the tool call, cwd, and recent task prompts. Probabilities map to verdicts via deny/ask thresholds, then authorization softens them.
Primitives:score
Technique worth stealing
Threshold probabilities into allow/ask/deny, then let an authorized mitigator soften one step on softenable axes only.
Try it
npm install -g @riskaverse/toolgate; export TYPESAFE_API_KEY=...; toolgate init
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 material0.81
- Shows a System One patternunclear0.52
- Describes handling uncertaintyunclear0.40
- Reports measured numbersFound in material0.66
- Is a runnable toolFound in material0.97
- Top-10 learning shortlist signalnot found in the excerpt0.17
- Is a replica of the modelnot found in the excerpt0.16
- Solves a common problem (0–2)score on a 0–2 scale1.50 / 2
- About JevFound in material0.99
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 1 Nov 2026.