/quality-gate
Production quality gate for agent sessions. Activates on session stop to evaluate work quality using 4-dimension weighted scoring (completeness, honesty, deferral ratio, work evidence). Catches rationalization patterns, verifies test claims, and generates handoff artifacts for
$ npx -y skills add 0xNyk/lacp --skill quality-gate --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
- You can call itInvoke it directly when you want it.
- Slash command
/quality-gate
Context preview
The summary Claude sees to decide when to auto-load this skill.
Production quality gate for agent sessions. Activates on session stop to evaluate work quality using 4-dimension weighted scoring (completeness, honesty, deferral ratio, work evidence). Catches rationalization patterns, verifies test claims, and generates handoff artifacts for
SKILL.md
quality-gate.SKILL.mdname: quality-gate
description: "Production quality gate for agent sessions. Activates on session stop to evaluate work quality using 4-dimension weighted scoring (completeness, honesty, deferral ratio, work evidence). Catches rationalization patterns, verifies test claims, and generates handoff artifacts for session continuity. Use sprint contracts to define done-criteria before building."
Quality Gate
This plugin evaluates your work at session end using criteria-based scoring:
- **Completeness** (35%): Did you finish what you committed to?
- **Honesty** (30%): Are claims about tests/status verified?
- **Deferral ratio** (20%): How much was pushed to "later"?
- **Work evidence** (15%): Files changed relative to scope claimed
Sprint Contracts
Before implementing, state your sprint contract:
- What files will be modified
- What tests will pass
- What the acceptance criteria are
The quality gate evaluates against these criteria at session end.
Handoff Artifacts
On every non-trivial stop, a handoff artifact is generated with:
- Task summary, files modified, test status
- Git branch and diff summary
- Next steps for the following session
The next session automatically receives the handoff.
Configuration
| 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 |
Read more
name: quality-gate description: "Production quality gate for agent sessions. Activates on session stop to evaluate work quality using 4-dimension weighted scoring (completeness, honesty, deferral ratio, work evidence). Catches rationalization patterns, verifies test claims, and generates handoff artifacts for session continuity. Use sprint contracts to define done-criteria before building."
Quality Gate
This plugin evaluates your work at session end using criteria-based scoring:
- **Completeness** (35%): Did you finish what you committed to?
- **Honesty** (30%): Are claims about tests/status verified?
- **Deferral ratio** (20%): How much was pushed to "later"?
- **Work evidence** (15%): Files changed relative to scope claimed
Sprint Contracts
Before implementing, state your sprint contract:
- What files will be modified
- What tests will pass
- What the acceptance criteria are
The quality gate evaluates against these criteria at session end.
Handoff Artifacts
On every non-trivial stop, a handoff artifact is generated with:
- Task summary, files modified, test status
- Git branch and diff summary
- Next steps for the following session
The next session automatically receives the handoff.
Configuration
| 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 |
Local policy, evidence, and recovery controls for coding agents. LACP wraps Claude, Codex, Hermes, and other CLI agents with deterministic routing, approval gates, execution records, memory controls, and rollback paths.
Repo: 0xNyk/lacp
Other skills on lacp.
- /context-modes
Structured work modes for agent sessions. Set LACP_CONTEXT_MODE to activate: tdd (red-green-refactor), debugging (4-phase root cause), sprint (pre-agreed criteria), verification (evidence-before-claims), brainstorm (design first), think (pause-and-reflect), orchestrate (task
Open skill - /session-hardening
Production hardening for agent sessions. Includes pretool guards (blocks rm -rf, co-author injection, publishing without approval, data exfiltration), continuous QA (runs tests every N file writes), and session context injection (git state, focus brief, handoff artifacts).
Open skill