Stats
Actions
Tags
'%20stop-opacity%3D'0.16'%2F%3E%3Cstop%20offset%3D'1'%20stop-color%3D'rgb(200%2C90%2C60)'%20stop-opacity%3D'0.03'%2F%3E%3C%2FlinearGradient%3E%3C%2Fdefs%3E%3Crect%20width%3D'320'%20height%3D'200'%20fill%3D'url(%23g)'%2F%3E%3Ccircle%20cx%3D'250'%20cy%3D'56'%20r%3D'92'%20fill%3D'rgb(200%2C90%2C60)'%20fill-opacity%3D'0.06'%2F%3E%3Ccircle%20cx%3D'64'%20cy%3D'172'%20r%3D'58'%20fill%3D'rgb(200%2C90%2C60)'%20fill-opacity%3D'0.05'%2F%3E%3C%2Fsvg%3E)
From lacp-hardening
Evaluates agent session work quality at end using 4D weighted scoring (completeness 35%, honesty 30%, deferral 20%, evidence 15%). Verifies tests, catches rationalizations, generates handoff artifacts with git diffs.
How this skill is triggered — by the user, by Claude, or both
Slash command
/lacp-hardening:quality-gateThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
This plugin evaluates your work at session end using criteria-based scoring:
This plugin evaluates your work at session end using criteria-based scoring:
Before implementing, state your sprint contract:
The quality gate evaluates against these criteria at session end.
On every non-trivial stop, a handoff artifact is generated with:
The next session automatically receives the handoff.
| Env Var | Default | Purpose |
|---|---|---|
LACP_QUALITY_GATE_THRESHOLD | 2.5 | Minimum weighted score (1-5) |
LACP_QUALITY_GATE_MODEL | llama3.1:8b | Ollama model for scoring |
LACP_BLIND_SPOT_ENABLED | 0 | Enable blind spot reflection |
npx claudepluginhub 0xnyk/lacp --plugin lacp-hardeningSelf-rates output on 5 axes (accuracy, completeness, clarity, actionability, conciseness) with evidence and a 1-5 scorecard. Useful after complex tasks to catch omissions and overconfidence.
Unifies accuracy validation, verification, and review-correction into a three-phase quality gate for agent output. Use before delivery or during rework.
Runs session-process evaluations against rubric-v1 dimensions using deterministic metrics from orchestrator sessions. Supports scoring, reporting, and reproducibility verification.