ReddRadar
Agent 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). Activates automatically via hooks.
Install this agent skill to your Project
npx add-skill https://github.com/0xNyk/lacp/tree/main/plugin/skills/session-hardening
SKILL.md
Session Hardening
This plugin provides three layers of production hardening:
Pretool Guard (PreToolUse)
Blocks dangerous operations before they execute:
rm -rf→ suggeststrashinstead- Co-author injection in commits
npm/cargo/pip publishwithout approvalcurl | python/nodedownload-first patternschmod 777→ suggests specific masksgit reset --hard,git clean -f- Data exfiltration via
curl --data @.env - Push to main on public repos
Continuous QA (PostToolUse)
Runs your project's test command at configurable intervals during work:
- Detects test command from package.json, Makefile, Cargo.toml, pyproject.toml
- Fires every N file writes (default: 10)
- Injects failure feedback without blocking
- Includes thinking prompt on failure (think mode)
Session Context (SessionStart)
Injects at every session start:
- Git branch, recent commits, modified files
- Focus brief (current problem, beliefs, decisions)
- Handoff artifact from previous session
- System health score
- Self-Memory System context
Configuration
| Env Var | Default | Purpose |
|---|---|---|
LACP_EVAL_CHECKPOINT_ENABLED |
0 |
Enable continuous QA |
LACP_EVAL_CHECKPOINT_INTERVAL |
10 |
Test every N writes |
LACP_CONTEXT_MODE |
`` | Active mode (tdd, debugging, sprint, etc.) |
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
0xNyk/lacp
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 session continuity. Use sprint contracts to define done-criteria before building.
0xNyk/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 decomposition). Each mode injects behavioral rules at session start.
davila7/claude-code-templates
verl-rl-training
Provides guidance for training LLMs with reinforcement learning using verl (Volcano Engine RL). Use when implementing RLHF, GRPO, PPO, or other RL algorithms for LLM post-training at scale with flexible infrastructure backends.
davila7/claude-code-templates
openrlhf-training
High-performance RLHF framework with Ray+vLLM acceleration. Use for PPO, GRPO, RLOO, DPO training of large models (7B-70B+). Built on Ray, vLLM, ZeRO-3. 2× faster than DeepSpeedChat with distributed architecture and GPU resource sharing.
davila7/claude-code-templates
gguf-quantization
GGUF format and llama.cpp quantization for efficient CPU/GPU inference. Use when deploying models on consumer hardware, Apple Silicon, or when needing flexible quantization from 2-8 bit without GPU requirements.
davila7/claude-code-templates
Claude Code Guide
Master guide for using Claude Code effectively. Includes configuration templates, prompting strategies "Thinking" keywords, debugging techniques, and best practices for interacting with the agent.
Didn't find tool you were looking for?