RickyTong1/audit-harness

Three-layer audit enforcement framework for AI agents — hooks, skills, context recovery, and audit-driven daily reports

472Stars on the repository
5Mods indexed here, across every type
2mo agoLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown

audit-end

01

RickyTong1/audit-harness

Skill Claude Code

A command for closing an audit session and checking that its records are complete. An audit session is a stored record of the tools used, files changed, and notes captured during a work period.

not rated 472 2mo ago A 63 tokens original MIT

audit-init

02

RickyTong1/audit-harness

Skill Claude Code

An installation wizard for an audit framework called `audit-harness`. It checks a new project, creates the required files and folders, and configures the project for audit tracking.

not rated 472 2mo ago A 45 tokens original MIT

audit-recover

03

RickyTong1/audit-harness

Skill Claude Code

A recovery procedure for finding earlier task context in audit records when the current conversation is incomplete. It uses session files, action logs, corrections, and conclusions.

not rated 472 2mo ago A 105 tokens original MIT

audit-report-daily

04

RickyTong1/audit-harness

Skill Claude Code

A daily work-report generator that reads audit records from a project’s `.claude/runs/` folder. It creates a report whose numbers can be traced back to those records.

not rated 472 2mo ago A 79 tokens original MIT

audit-start

05

RickyTong1/audit-harness

Skill Claude Code

A command that starts an audit session for a task and restores relevant context from earlier sessions. The session stores the task description and links later audit records to it.

not rated 472 2mo ago A 102 tokens original MIT

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: