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/legioncodeinc/honeycomb/user-prompt-submitgit clone --depth 1 https://github.com/legioncodeinc/honeycombGrade A, and why
UserPromptSubmit 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.
The source is not reproduced here
Licensed AGPL-3.0
The repository is licensed AGPL-3.0, which this catalogue does not treat as permission to reproduce the file. Read it at the source.
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.
- 2d ago First seen · 23 lines scan A 4381e59f3cad
UserPromptSubmit is a hook published in the GitHub repository legioncodeinc/honeycomb (110 stars, last pushed 1mo ago), licensed AGPL-3.0. 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
SessionStart
Runs when a session starts, executing check-trash.sh and session-start-hooks-bootstrap.sh (2 commands). From TserenTserenov/FMT-exocortex-template.
PreCompact
Runs before the context is compacted, executing precompact-checkpoint.sh. From TserenTserenov/FMT-exocortex-template.
SessionStart
Runs when a session starts, executing update-check.js via node. From KevinZai/commander.
PreToolUse
Runs before the agent uses a tool for Read, Write, Edit, MultiEdit, NotebookEdit, Bash, Edit, Write, Edit, Write, Bash, Edit, Write, MultiEdit, Write, Edit, MultiEdit, NotebookEdit, Bash, mcp__.*, Skill and mcp__.* tool calls, executing pull-on-touch.sh, extensions-gate.sh, inject-code-style.sh, destructive-guard.sh…
Stop
Runs when the agent finishes a response, executing protocol-stop-gate.sh, capture-bus.sh and response-clarity-hook.sh (3 commands). From TserenTserenov/FMT-exocortex-template.
PostToolUse
Runs after a tool call finishes for ^(Task, Agent)$, ^(?:.*__)?search_ruvnet$, Write, Edit, MultiEdit, Bash, Write, Edit, MultiEdit and ^Bash$ tool calls, executing hook-shim.mjs via node (5 commands). From stuinfla/ruvnet-brain.