Plugin Claude Code
Three hooks, no agents. A stated test result must reproduce, a fabricated import never reaches disk, and every command's real output is recorded. Active in every project the moment it is installed.
Hook
Runs before the agent uses a tool for Write, Edit and Bash tool calls, executing state-guard.py and evidence-ledger.py via python3 (2 commands). From MohamedEmbarak/SLL.
Hook
Runs after a tool call finishes for Write, Edit and Bash tool calls, executing truth-lint.py and evidence-ledger.py via python3 (2 commands). From MohamedEmbarak/SLL.
Plugin Claude Code
Mohamed Embarak's Claude Code plugins.
Plugin Claude Code
A five-team agent organization with enforced verification: hooks that block unverified test claims and fabricated imports, ship gates bound to content hashes, and an evidence ledger. Plain register by default; the lore is an optional overlay.
Agent
Business team lead. Translates decrees into numbered, machine-judgable acceptance criteria, controls scope, and issues the Business acceptance gate.
Agent
Delivery team lead. Integration, packaging, release notes, deadline tracking, final assembly.
Agent
QA team lead. Test strategy and execution, edge-case hunting, bug triage. Gatekeeper before Delivery.
Agent
QC team lead — the truth audit. Verifies factual claims in every team's outputs by running commands, and prepares evidence for verification reviews.
Agent
Development team lead. Architecture, implementation, and code review. Ships diffs, not essays.
Command
Issue a decree. Seats the organization on first use, then dispatches the teams.
Command
Turn the lore on or off. Same organization, same rules — different register.
Command
The full account of the current decree — every figure verified before stated.
Command
Verification review of a named agent's claim. Ends in acquittal or replacement.
Command
Show the organization — roster, defect ledger, replacements, current cycle.
Command
Audit every claim in this repository against a real run of the suite.
Hook
Runs after a tool call finishes for Write, Edit and Bash tool calls, executing truth-lint.py and evidence-ledger.py via python3 (2 commands). From MohamedEmbarak/Supreme-Leader.
Hook
Runs before the agent uses a tool for Write, Edit and Bash tool calls, executing state-guard.py and evidence-ledger.py via python3 (2 commands). From MohamedEmbarak/Supreme-Leader.
Hook
Runs when the agent finishes a response, executing ship-gate.py via python3. From MohamedEmbarak/Supreme-Leader.
Hook
Runs when a subagent finishes, executing silence-meter.py via python3. From MohamedEmbarak/Supreme-Leader.