Automated README summary
Automatically summarized from the README on 20 Sept 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
limpet is a Stop hook for coding agents. You write completion rules in plain language; every time the agent is about to stop, limpet checks the stop against those rules and sends the agent back to work if a rule is violated.
How it uses Jev
On each stop, limpet reads the last 3 messages, this turn's tool calls, and the final message, then asks jev one yes/no question per rule in parallel. Each rule gets a probability; rules over threshold cause exit 2 with one line on stderr, so the agent keeps working.
Primitives:choice
Technique worth stealing
Judge plain-language stop rules with one yes/no question per rule over recent messages and tool calls, tuning for recall.
Try it
Install via Claude Code or Codex plugin, or clone and add a Stop hook running python3 ~/limpet/limpet.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-1.13.0- 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 material0.89
- Shows a System One patternFound in material0.82
- Describes handling uncertaintynot found in the excerpt0.05
- Reports measured numbersunclear0.45
- Is a runnable toolFound in material0.95
- Top-10 learning shortlist signalnot found in the excerpt0.29
- Is a replica of the modelnot found in the excerpt0.03
- Solves a common problem (0–2)score on a 0–2 scale1.26 / 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 20 Sept 2026.