Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add MohamedEmbarak/Supreme-Leader/plugin install slWrote 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/verify)<a href="https://agentmods.dev/commands/mohamedembarak/supreme-leader/verify"><img src="https://agentmods.dev/badge/commands/mohamedembarak/supreme-leader/verify/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/verify"><img src="https://agentmods.dev/badge/commands/mohamedembarak/supreme-leader/verify.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 | $0.00236 |
| Opus 5 | $0.00007 | $0.00118 |
| Sonnet 5 | $0.00003 | $0.00047 |
| Haiku 4.5 | $0.00001 | $0.00024 |
Grade A, and why
verify scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Run the repository-wide claim audit:
python3 "${CLAUDE_PLUGIN_ROOT}/hooks/verify-claims.py"
It detects the project's test suite — Python unittest or pytest, Node via
npm test, or Go — runs it once, then checks every stated test figure in every
markdown file against what actually ran. Exit 0 means every claim reproduces.
Report the result plainly. On failures, list each offending file and line, then fix
the figures or mark them UNVERIFIED. Do not silence a finding by deleting the claim
unless the claim was genuinely wrong to make.
A file that records measurements from a past run — an audit log, a changelog — may
declare itself historical with an HTML comment reading truth-lint: historical, at
the top of the file for the whole file, or at the end of a line for that line alone.
Use it sparingly and only for genuine records: the marker is greppable precisely so
the next auditor can see every exemption at a glance.
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 · 24 lines · 14 tokens per session scan A bdb17f683d76
verify 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 236 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
fable-eval
Run the fable-mode eval suite (probes → pairwise judge → report). Costs tokens — runs headless claude many times. Optional arg: a probe id substring to filter.
gather
Phase 40 — merge completed SPs in wave order, run per-SP regression, update wave-status.
plan-validate
2-layer plan validation: instant structural checks + trigger-based specialist agents. Auto-fixes issues using ADRs and first principles. Every issue must be resolved before execution.
generate-tests
Generate comprehensive tests for specified code.
record
Record a browser walkthrough of a URL using Antigravity (agy). Generates .webm video, screenshots, and a report. Auto-converts to MP4 if ffmpeg is available.
review-skills
Review changed skills: automated bash checks + 9 structural dimensions (D1-D9) + 5 intent checks (M1-M5). PASS/FAIL verdict. Fix in-place.