Automated README summary
Automatically summarized from the README on 3 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
firstlight reads public Certificate Transparency logs to find domains imitating Irish banks, An Post, Revenue, HSE and others. It is for defenders who want lead time before phishing sites go live.
How it uses Jev
For each candidate domain that survives the brand filter, Jev returns a calibrated probability that it is an impersonation attempt. Verdicts above a threshold are stored in SQLite and exported to a static dashboard.
Primitives:score
Technique worth stealing
Use a generous pre-filter to cut a firehose to candidates, then let a calibrated decision model handle precision.
Try it
python watch.py --once --no-jev for a filter-only pass; set OPENROUTER_API_KEY to enable Jev scoring.
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-1.13.0- Project signals
jev-1.13.0- Category
jev-1.13.0- Pattern tags
jev-1.13.0
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 material0.87
- Shows a System One patternFound in material0.71
- Describes handling uncertaintynot found in the excerpt0.05
- Reports measured numbersFound in material0.95
- Is a runnable toolunclear0.53
- Top-10 learning shortlist signalnot found in the excerpt0.34
- Is a replica of the modelnot found in the excerpt0.03
- Solves a common problem (0–2)score on a 0–2 scale1.04 / 2
- About JevFound in material0.96
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 3 Oct 2026.