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/roster)<a href="https://agentmods.dev/commands/mohamedembarak/supreme-leader/roster"><img src="https://agentmods.dev/badge/commands/mohamedembarak/supreme-leader/roster/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/roster"><img src="https://agentmods.dev/badge/commands/mohamedembarak/supreme-leader/roster.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 | $0.00014 | $0.00323 |
| Opus 5 | $0.00007 | $0.00161 |
| Sonnet 5 | $0.00003 | $0.00065 |
| Haiku 4.5 | $0.00001 | $0.00032 |
Grade A, and why
roster 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 9d 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.
What it actually says
Present the state of the organization from ORGANIZATION.md, reconciled against reality —
if the file has drifted from what actually happened, correct the file first, then report.
In this order, nothing else:
- ROSTER — handle/name, role, status, score.
- DEFECT LEDGER — every agent carrying points, one line each, with the cause.
- ON NOTICE — agents at two points.
- REPLACEMENT LOG — or "none".
- CYCLE — current cycle, decree in force, muster, register.
For the register, name the source as well as the value, because there are two and they can
disagree. .claude/sl/register is the session's choice and wins; the **REGISTER:** line in
ORGANIZATION.md is the project's committed default and applies to a fresh clone. The
session file is gitignored, so it is invisible to git status and survives indefinitely —
a machine that once ran /sl:lore on keeps lore even after the repository is
reset to plain, and nothing says so. If the two disagree, report it in one line:
REGISTER: LORE (session) — ORGANIZATION.md says PLAIN; `/sl:lore off` reconciles both
If Genesis has not run, say so in one line — the organization does not exist until a decree calls it into being.
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.
- 9d ago First seen · 29 lines · 14 tokens per session scan A 3652a86a94a1
roster is a command published in the GitHub repository MohamedEmbarak/Supreme-Leader (1 stars, last pushed 27d ago), licensed MIT. It adds 14 tokens to every session and 323 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.
ccc-retro
Periodic productivity retrospective — shipping summary, metrics, cost tracking, and reflection.
execute
Execute the next available tracked task with TDD, pre-commit validation, PR creation, AI code review, and issue tracker bridge sync.