Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add hooks/open-metadata/openmetadata/pre-tool-usegit clone --depth 1 https://github.com/open-metadata/OpenMetadataGrade A, and why
PreToolUse scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the commands this hook runs, not an audit. A hook is shell that executes on your machine at the event it names, which is why every command in it is printed with what was found.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 39 lines — stays where its author put it; the contents beside it link to each section on GitHub.
{
"PreToolUse": [
{
"matcher": "Bash",
"hooks": [
{
"type": "command",
"command": "if echo \"$CLAUDE_TOOL_INPUT\" | grep -q -- '--no-verify'; then echo '{\"decision\": \"block\", \"reason\": \"Do not skip pre-commit hooks with --no-verify. Fix the underlying issue instead.\"}'; exit 2; fi",
"description": "Block --no-verify on git commits"
}
]
},
{
"matcher": "Edit|Write",
"hooks": [
{
"type": "command",
"command": "FILE=$(echo \"$CLAUDE_TOOL_INPUT\" | jq -r '.file_path // empty' 2>/dev/null); if [ -n \"$FILE\" ] && echo \"$FILE\" | grep -qE '(openmetadata-ui/src/main/resources/ui/src/generated/|ingestion(-core)?/src/metadata/generated/|/target/generated-sources/)'; then echo '{\"decision\": \"block\", \"reason\": \"Blocked write to GENERATED output. This file is produced by code generation (jsonschema2pojo / datamodel-code-generator / quicktype / ANTLR); hand edits are overwritten by the next build and, for the committed UI types, reverted by the typescript-type-generation CI job. Edit the JSON Schema under openmetadata-spec/src/main/resources/json/schema/ and run make generate (a repo-root-only target). See .claude/rules/schema-first.md.\"}'; exit 2; fi",
"description": "Block edits to generated output; direct to the schema + make generate"
},
{
"type": "command",
"command": "FILE=$(echo \"$CLAUDE_TOOL_INPUT\" | jq -r '.file_path // empty' 2>/dev/null); if [ -n \"$FILE\" ] && echo \"$FILE\" | grep -qE 'docs/generated/(entity-index|api-reference)\\.md'; then echo '{\"decision\": \"block\", \"reason\": \"Blocked write to a GENERATED reference doc. docs/generated/entity-index.md and api-reference.md are produced by scripts/generate_entity_index.py and scripts/generate_api_reference.py; hand edits are reverted by the reference-docs freshness CI job. Change the source instead (JSON Schemas under openmetadataWhat this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 39 lines scan A eeef0dcf8463
PreToolUse is a hook published in the GitHub repository open-metadata/OpenMetadata (15,059 stars, last pushed today), licensed Apache-2.0. Its token cost is not measured: a hook is shell that never enters the context. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other hooks, from other repositories
PreToolUse
Runs before the agent uses a tool for Bash tool calls, executing deny-git-no-verify.sh. From datahub-project/datahub.
PostToolUse
Runs after a tool call finishes for Edit and Write tool calls, executing auto-format-go.sh, auto-lint-ts.sh and auto-graphql-codegen.sh via bash with --show-toplevel (3 commands). From clidey/whodb.
SessionStart
Runs when a session starts, executing session-context.sh via bash with --show-toplevel. From clidey/whodb.
Stop
Runs when the agent finishes a response, executing verify-build.sh via bash with --show-toplevel. From clidey/whodb.
Stop
Runs when the agent finishes a response, running an inline shell check. From anam-org/metaxy.
SessionStart
Runs when a session starts on startup, resume, clear and compact, running an inline shell check. From bigbio/sdrf-skills.