Skill

session-hardening

Hardens production agent sessions with pretool guards blocking rm -rf, data exfiltration, unsafe publishes; continuous QA running tests every N file writes; git state and focus context injection. Auto-activates via hooks.

Git

npx claudepluginhub 0xnyk/lacp --plugin lacp-hardening

Popularity

Parent stars

257

Parent forks

Invocation

How this skill is triggered — by the user, by Claude, or both

Slash command

/lacp-hardening:session-hardening

User invocable

Model invocable

Inline context

Default effort

Context Preview

The summary Claude sees in its skill listing — used to decide when to auto-load this skill

This plugin provides three layers of production hardening:

SKILL.md

46 lines · ~424 tokens

Similar Skills

safety-guard

213.5k

Prevents destructive operations on production systems and autonomous agents by intercepting dangerous commands, restricting edits to a directory, or combining both protections.

ecc

Guardrails Enforcement Agent

Enforces the Four Laws of Agent Safety on all operations, halting when uncertain. Ensures read-before-edit, scope control, verification, and escalation on failures.

agent-guardrails

cc-safe-setup

Installs 695 safety hooks that prevent file deletion, credential leaks, git disasters, and token waste during autonomous AI coding sessions.

cc-safe-setup

Stats

LanguageShell

Parent stars257

Parent forks33

MaintenanceGood

Last CommitApr 9, 2026

Actions

View Source View Plugin View on GitHub View README

Help us improve

Share bugs, ideas, or general feedback.

Stats

Actions

Help us improve

Share bugs, ideas, or general feedback.

Session Hardening

This plugin provides three layers of production hardening:

Pretool Guard (PreToolUse)

Blocks dangerous operations before they execute:

rm -rf → suggests trash instead

Co-author injection in commits

npm/cargo/pip publish without approval

curl | python/node download-first patterns

chmod 777 → suggests specific masks

git 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.)