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/azalio/map-framework/user-prompt-submitgit clone --depth 1 https://github.com/azalio/map-frameworkGrade 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.
This is a copy
52% identical to SessionStart — 32 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
{
"UserPromptSubmit": [
{
"description": "Clarification & Durability Trigger Detection",
"hooks": [
{
"type": "command",
"command": "\"$CLAUDE_PROJECT_DIR\"/.claude/hooks/detect-clarification-triggers.py",
"timeout": 3,
"description": "Detects user-invited clarification language and async/durability language; injects guidance for /map-plan and task-decomposer"
}
]
},
{
"description": "Context Meter - inject /compact nudge when token threshold crossed",
"hooks": [
{
"type": "command",
"command": "\"$CLAUDE_PROJECT_DIR\"/.claude/hooks/context-meter.py",
"timeout": 5,
"description": "Reads transcript token usage; if compression_policy=auto/aggressive and threshold crossed, injects additionalContext suggesting /compact"
}
]
},
{
"description": "MAP Memory Recall",
"hooks": [
{
"type": "command",
"command": "\"$CLAUDE_PROJECT_DIR\"/.claude/hooks/map-memory-recall.py",
"timeout": 10,
"description": "Inject ranked recalled session memory"
}
]
}
]
}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 · 37 lines scan A 03424e6eb211
UserPromptSubmit is a hook published in the GitHub repository azalio/map-framework (153 stars, last pushed 4d ago), licensed MIT. 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. It is 52% identical to SessionStart, differing in 32 lines, and is treated as a copy.
Other hooks, from other repositories
PostToolUse
Runs after a tool call finishes for Edit, Write, MultiEdit and Bash tool calls, executing clad.js via node. From qwerfunch/cladding.
SessionStart
Runs when a session starts, executing clad.js via node. From qwerfunch/cladding.
SessionStart
Runs when a session starts, executing session-start.js via node. From Codename-11/SubFrame.
UserPromptSubmit
Runs when you submit a prompt, before the agent sees it, executing prompt-submit.js via node. From Codename-11/SubFrame.
Stop
Runs when the agent finishes a response, executing stop.js via node. From Codename-11/SubFrame.
PreToolUse
Runs before the agent uses a tool, executing pre-tool-use.js via node. From Codename-11/SubFrame.