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/t-rav/hydraflow/pre-tool-usegit clone --depth 1 https://github.com/T-rav/hydraflowGrade 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 3d 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 — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
{
"PreToolUse": [
{
"matcher": "Bash",
"hooks": [
{
"type": "command",
"command": "\"$CLAUDE_PROJECT_DIR\"/.claude/hooks/hf.block-destructive-git.sh",
"timeout": 10,
"statusMessage": "Checking for destructive git commands...",
"_hydraflow": true
},
{
"type": "command",
"command": "\"$CLAUDE_PROJECT_DIR\"/.claude/hooks/hf.scan-secrets-before-commit.sh",
"timeout": 30,
"statusMessage": "Scanning for secrets in staged files...",
"_hydraflow": true
},
{
"type": "command",
"command": "\"$CLAUDE_PROJECT_DIR\"/.claude/hooks/hf.validate-tests-before-commit.sh",
"timeout": 120,
"statusMessage": "Validating lint + tests before commit...",
"_hydraflow": true
},
{
"type": "command",
"command": "\"$CLAUDE_PROJECT_DIR\"/.claude/hooks/hf.validate-functional-areas.sh",
"timeout": 30,
"statusMessage": "Validating functional-areas schema...",
"_hydraflow": true
}
]
},
{
"matcher": "Write",
"hooks": [
{
"type": "command",
"command": "\"$CLAUDE_PROJECT_DIR\"/.claude/hooks/hf.enforce-plan-and-explore.sh",
"timeout": 10,
"statusMessage": "Checking for exploration and planning...",
"_hydraflow": true
},
{
"type": "command",
"command": "\"$CLAUDE_PROJECT_DIR\"/.claude/hooks/hf.check-test-counterpart.sh",
"timeout": 10,
"statusMessage": "Checking for test counterpart...",
"_hydraflow": true
},
{
"type": "command",
"command": "\"$CLAUDE_PROJECT_DIR\"/.claude/hooks/hf.enforce-migrations.sh",
"timeout": 10,
"statusMessage": "Checking for direct DB schema changes...",
"_hydraflow": true
},
What 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.
- 3d ago First seen · 103 lines scan A e81425b21d5c
PreToolUse is a hook published in the GitHub repository T-rav/hydraflow (5 stars, last pushed 3d ago), 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 2026-08-31.
Other hooks, from other repositories
PreToolUse
Runs before the agent uses a tool, executing hooks.py via python3. From shanraisshan/shanraisshan.
PermissionRequest
Runs when the agent asks permission for an action, executing hooks.py via python3. From shanraisshan/shanraisshan.
PostToolUse
Runs after a tool call finishes, executing hooks.py via python3. From shanraisshan/shanraisshan.
PostToolUseFailure
Runs when a tool call fails, executing hooks.py via python3. From shanraisshan/shanraisshan.
UserPromptSubmit
Runs when you submit a prompt, before the agent sees it, executing hooks.py via python3. From shanraisshan/shanraisshan.
Notification
Runs when the agent sends a notification, executing hooks.py via python3. From shanraisshan/shanraisshan.