plugins/src/base/skills/parity-safety-net-rules/SKILL.md
View, set, and verify the custom guard rules enforced by Lisa's safety-net PreToolUse Bash hook (parity-safety-net.sh). The consolidated cross-agent equivalent of the upstream safety-net plugin's set-custom-rules + verify-custom-rules skills — manages a project-local list of extended-regex patterns that block destructive shell commands, on Codex, agy, Copilot, Cursor, and Claude.
npx skillsauth add codyswanngt/lisa parity-safety-net-rulesInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Manage the custom guard rules that Lisa's safety-net hook enforces on every
Bash command. The hook (hooks/parity-safety-net.sh, registered as a
PreToolUse matcher on Bash) ships with built-in guards against catastrophic
commands; this skill lets a project view, set, and verify additional
project-specific rules on top of those built-ins.
Lisa-native reimplementation. This consolidates the upstream
safety-net@cc-marketplaceplugin's two rule-management skills (set-custom-rules+verify-custom-rules) into one. It is reimplemented from scratch against Lisa conventions — it does not port or invoke upstream plugin code.Drift tracking. Pinned to
safety-net@[email protected].scripts/plugin-parity-drift.mjscompares this pin against the upstream version in the plugin cache and flags staleness. Do not port or copy upstream plugin code.
# are
ignored. Matching is case-insensitive (grep -Ei).Resolved in this order:
$SAFETY_NET_RULES_FILE (explicit override), else${CLAUDE_PROJECT_DIR:-$PWD}/.claude/safety-net-rules.txtRULES_FILE="${SAFETY_NET_RULES_FILE:-${CLAUDE_PROJECT_DIR:-$PWD}/.claude/safety-net-rules.txt}"
rm -rf of a filesystem root, $HOME/~, or a top-level wildcard.main/master/production/release).
--force-with-lease is intentionally allowed.git reset --hard while the working tree is dirty (would discard work).DROP DATABASE/SCHEMA/TABLE, TRUNCATE TABLE.RULES_FILE="${SAFETY_NET_RULES_FILE:-${CLAUDE_PROJECT_DIR:-$PWD}/.claude/safety-net-rules.txt}"
if [ -f "$RULES_FILE" ]; then
echo "Custom safety-net rules ($RULES_FILE):"
grep -vE '^[[:space:]]*(#|$)' "$RULES_FILE" || echo "(no active rules)"
else
echo "No custom rules file yet ($RULES_FILE). Only built-in guards are active."
fi
Read the file to show comments and structure as well.
A rule is an ERE matched against the full command string. Keep rules specific to avoid blocking legitimate work — anchor on the dangerous verb and its target.
Ensure the file exists, then append a commented rule (use Edit/Write,
or append from the shell):
RULES_FILE="${SAFETY_NET_RULES_FILE:-${CLAUDE_PROJECT_DIR:-$PWD}/.claude/safety-net-rules.txt}"
mkdir -p "$(dirname "$RULES_FILE")"
{
echo "# Block deleting a Kubernetes namespace"
echo 'kubectl[[:space:]]+delete[[:space:]]+namespace'
} >> "$RULES_FILE"
Always verify the new rule (next section) before considering it set — confirm it blocks what it should and allows what it shouldn't.
Editing/removing: open the file with Edit and change or delete the line.
Removing a rule never affects the built-in guards.
Two checks — both should pass before you trust a rule.
An invalid regex would make the hook error on every command. Validate it:
printf '%s' "$RULE" | grep -Eq -- "$RULE" 2>/dev/null && echo "valid ERE" \
|| echo "INVALID ERE — fix before saving"
Drive the actual hook with a fake PreToolUse payload and assert the exit
code (non-zero = blocked, 0 = allowed). Build the JSON with jq so the test
command line itself never contains the dangerous literal:
HOOK="${CLAUDE_PLUGIN_ROOT}/hooks/parity-safety-net.sh"
check() { # check <expect: block|allow> <command>
jq -nc --arg c "$2" '{tool_name:"Bash",tool_input:{command:$c}}' \
| bash "$HOOK" >/dev/null 2>&1
local code=$?
local got=allow; [ "$code" -ne 0 ] && got=block
printf '%-5s want=%-5s got=%-5s %s\n' \
"$([ "$got" = "$1" ] && echo OK || echo FAIL)" "$1" "$got" "$2"
}
# Should block (matches the new rule):
check block "kubectl delete namespace prod"
# Should allow (must not over-match):
check allow "kubectl get pods"
Report a table of cases with want/got/verdict. If any case disagrees, tighten the ERE and re-verify.
development
Prepare a machine — a fresh laptop or a throwaway container — to run coding agents, before any repository exists. Detects which of Lisa's supported agents (Claude Code, Codex, Cursor, OpenCode, Antigravity, Copilot) are already installed, asks which credential manager the machine uses (Bitwarden, 1Password, Doppler, Vault, AWS, or none), and installs only what is missing, each by its vendor's own preferred method. Idempotent, headless by default, and emits a Dockerfile for a spin-up/spin-down environment. Run it on a new machine, in a container, or before cloning anything.
tools
Provision and verify a remote execution environment for a host project — Codex Cloud today, other remote surfaces as they are added. Generates a repository-owned setup script that installs the declared toolchain, materializes secrets through lisa-secrets-access, and runs the project's own hook. Provisions by API where one exists, by driving the vendor console where one does not, and by emitting exact config otherwise — then proves the result with the same read-back regardless of which tier did the work. Use before dispatching any work with executionEnv.
tools
Bring a developer's machine in line with the toolchain the project declares. Reports every tool in remoteEnv.tools that is missing, outdated, or unpinned for this platform, and installs the missing ones into ~/.local/bin from the same pinned, checksummed entries the remote surfaces use — but only when asked. Same manifest, same pins, same installers as lisa-setup-remote-env; what differs is consent and that the pin is a floor rather than an equality. Run it on a fresh checkout, after a manifest change, or when a tool fails at the moment of use.
tools
Route one unit of work to a remote execution surface. Reads the executionEnv parameter (local by default, codex-cloud or claude-web today), verifies the environment is provisioned and bound to this repository, submits a thin skill invocation, records the task identifier to .lisa/remote-dispatch.json, and exits without polling. Routing only — the remote runs the identical skill from the identical repository. Composable and inline: other skills invoke it via the Skill tool rather than users calling it directly.