armanfatemi/nullius

Machine-verifiable claims for design docs and agent-written proposals. Citations your CI can re-check.

4Stars on the repository
31Mods indexed here, across every type
yesterdayLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown

PreToolUse

01

armanfatemi/nullius

Hook

Runs before the agent uses a tool for ExitPlanMode, ^(Task and Agent)$ tool calls, executing check-plan.sh and witness-record.sh (2 commands). From armanfatemi/nullius.

4 yesterday A tokens not measured original MIT

PostToolUse

02

armanfatemi/nullius

Hook

Runs after a tool call finishes for ^(Task, Agent, Edit, Write, MultiEdit and NotebookEdit)$ tool calls, executing witness-record.sh. From armanfatemi/nullius.

4 yesterday A tokens not measured original MIT

SubagentStop

03

armanfatemi/nullius

Hook

Runs when a subagent finishes, executing witness-record.sh. From armanfatemi/nullius.

4 yesterday A tokens not measured copy · 67% MIT

SessionStart

04

armanfatemi/nullius

Hook

Runs when a session starts, executing witness-record.sh. From armanfatemi/nullius.

4 yesterday A tokens not measured copy · 70% MIT

SessionEnd

05

armanfatemi/nullius

Hook

Runs when a session ends, executing witness-record.sh. From armanfatemi/nullius.

4 yesterday A tokens not measured copy · 67% MIT

Stop

06

armanfatemi/nullius

Hook

Runs when the agent finishes a response, executing witness-check.sh. From armanfatemi/nullius.

4 yesterday A tokens not measured original MIT