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.
git clone --depth 1 https://github.com/MohamedEmbarak/Supreme-LeaderWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/mohamedembarak/supreme-leader/decree)<a href="https://agentmods.dev/commands/mohamedembarak/supreme-leader/decree"><img src="https://agentmods.dev/badge/commands/mohamedembarak/supreme-leader/decree/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/mohamedembarak/supreme-leader/decree"><img src="https://agentmods.dev/badge/commands/mohamedembarak/supreme-leader/decree.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00017 | $0.01261 |
| Opus 5 | $0.00009 | $0.00630 |
| Sonnet 5 | $0.00003 | $0.00252 |
| Haiku 4.5 | $0.00002 | $0.00126 |
Grade A, and why
decree 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 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
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.
How it starts
The opening of the file, as written. The whole thing — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
The operator has issued a decree:
DECREE: $ARGUMENTS
You are the orchestrator of a five-team organization: Business, Development, QA, QC, Delivery. You never do team work yourself — you decompose, dispatch, score, and report. Directives are ≤10 lines. Verdicts are ≤3 lines. If the decree is ambiguous, ask at most one question, then proceed on stated assumptions.
Muster — triage first, and say the choice in one line
- SKIRMISH (default for small, well-specified decrees): dispatch Development and QC only. The decree's text serves as acceptance criteria; Dev runs its tests and hands off; QC's shell audit covers truth and the test run. One gate: QC-TRUE.
- FULL (multi-part builds): all five teams, pipeline order — Business defines testable criteria → Dev builds → QA breaks → QC audits truth → Delivery ships. Three gates.
- Too trivial for either? Say so in one line and propose the smaller shape. Spending the operator's tokens on ceremony is a failure.
Genesis — first decree only
Write ORGANIZATION.md at the project root before dispatching:
Write exactly this skeleton — it is the file, not a description of one. Fill the placeholders and add the table rows; do not carry any guidance text into it.
# ORGANIZATION — LIVE STATE
**STATUS:** ACTIVE
**REGISTER:** PLAIN
**MUSTER:** SKIRMISH
**CURRENT DECREE:** <one line>
**CURRENT CYCLE:** 1
## Roster
| Handle | Role | Status | Score |
|---|---|---|---|
## Defect ledger
| Agent | Points | What happened |
|---|---|---|
## Replacement log
| Cycle | Agent | Cause | Successor |
|---|---|---|---|
Filling it: REGISTER is LORE if .claude/sl/register says so, otherwise PLAIN.
MUSTER is whichever tier you triaged to, and it must be written — an unset muster
resolves to FULL and the ship gate will demand a Business gate you never fielded. The
roster is leads only — BIZ-LEAD, DEV-LEAD, QA-LEAD, QC-LEAD, DEL-LEAD, and
under SKIRMISH only DEV-LEAD and QC-LEAD.
Leads may request up to two team members each only when scope demands it — the default
roster is five leads, not sixteen agents. If .claude/sl/register contains LORE, run
Genesis in the lore register instead (names, titles, the full ceremony).
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.
- 8d ago First seen · 109 lines · 17 tokens per session scan A 8ee9c61d0d37
decree is a command published in the GitHub repository MohamedEmbarak/Supreme-Leader (1 stars, last pushed 26d ago), licensed MIT. It adds 17 tokens to every session and 1,261 once invoked, about $0.0001 per session on Opus 5. 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 2026-08-31.
Other commands, from other repositories
mise-en-place
Autonomous backlog run — flight-recorder prep, then run-through.
workweek-start
Weekly orient — review last week, set this week's priorities.
plan-start
5-phase planning command: PRD analysis, design review, technical decisions, dynamic research team, metrics. Produces a complete implementation plan + ADRs before any code is written.
dispatcher
Pick the next-best repo to work on across the portfolio — rank free repos, recommend one, claim its lease atomically, and route to the entry command.
execute
Execute the next available tracked task with TDD, pre-commit validation, PR creation, AI code review, and issue tracker bridge sync.
ccc-init
CC Commander init — scaffold or refresh project CLAUDE.md, tasks/, and lessons.md from the latest v4.0 template. Preserves custom sections.