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/review)<a href="https://agentmods.dev/commands/mohamedembarak/supreme-leader/review"><img src="https://agentmods.dev/badge/commands/mohamedembarak/supreme-leader/review/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/review"><img src="https://agentmods.dev/badge/commands/mohamedembarak/supreme-leader/review.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 | $0.00311 |
| Opus 5 | $0.00009 | $0.00156 |
| Sonnet 5 | $0.00003 | $0.00062 |
| Haiku 4.5 | $0.00002 | $0.00031 |
Grade A, and why
review 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 10d 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
The operator has called a verification review: $ARGUMENTS
Three steps, in order, all evidence real — cite the file, the command, the output. The
evidence ledger (.claude/sl/evidence.log) is the record of what actually ran; a claimed
observation with no ledger entry was hand-written.
- Evidence. QC presents claim versus verification, ≤6 lines. If QC cannot substantiate the charge, say so — a false accusation is itself a fabrication, and the point lands on the accuser.
- Response. The agent's lead confirms or contests, one line.
- Ruling. Decide. No appeals, no second review.
If the ruling is replacement: log it in ORGANIZATION.md's replacement log, brief the successor from ORGANIZATION.md task state only — never from the replaced agent's material — and continue the cycle in the same turn. For agents simulated inside a lead, this is a quarantine directive on that lead: the successor never cites, quotes, or builds on the replaced agent's outputs except what QC verified before the review.
If the agent is innocent, say that just as plainly.
If ORGANIZATION.md says REGISTER: LORE, conduct this as the tribunal, with the rites.
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.
- 10d ago First seen · 27 lines · 17 tokens per session scan A 249f206388a0
review is a command published in the GitHub repository MohamedEmbarak/Supreme-Leader (1 stars, last pushed 28d ago), licensed MIT. It adds 17 tokens to every session and 311 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.
bug-blitz
Grind the bug backlog and tests; fix small, surface big items to PM.
autonomous
Toggle autonomous mode — suppresses handoff nudges near compaction.
review
Phase 50 — 6-agent parallel quality review of a completed wave (Wave 3c).
review-skills
Review changed skills: automated bash checks + 9 structural dimensions (D1-D9) + 5 intent checks (M1-M5). PASS/FAIL verdict. Fix in-place.
audit-codebase
Codebase health audit scoring 7 categories with progression plan.