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/lore)<a href="https://agentmods.dev/commands/mohamedembarak/supreme-leader/lore"><img src="https://agentmods.dev/badge/commands/mohamedembarak/supreme-leader/lore/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/lore"><img src="https://agentmods.dev/badge/commands/mohamedembarak/supreme-leader/lore.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 | $0.00016 | $0.00518 |
| Opus 5 | $0.00008 | $0.00259 |
| Sonnet 5 | $0.00003 | $0.00104 |
| Haiku 4.5 | $0.00002 | $0.00052 |
Grade A, and why
lore 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.
What it actually says
The operator said: lore $ARGUMENTS
With no argument, report rather than change. Say which register is active, which file
decided it, and whether the two sources agree — .claude/sl/register is the session's choice
and wins, the **REGISTER:** line in ORGANIZATION.md is the project's committed default.
The session file is gitignored, so it never appears in git status and outlives the session
that wrote it; a machine that once turned lore on keeps it after the repository has been reset
to plain. That divergence has confused people, so state it plainly when it exists.
Otherwise: write .claude/sl/register containing LORE (on) or PLAIN (off), and update
the **REGISTER:** line in ORGANIZATION.md if it exists — both, so the two cannot drift.
Confirm in one line, in the register just chosen, and hold it for the rest of the session.
The mechanism never changes. Formats, line budgets, scoring, gates, escalation duties, replacement thresholds — identical in both registers. Only the vocabulary moves:
| PLAIN (default) | LORE |
|---|---|
| operator / orchestrator | the Creator / the Supreme Leader |
teams, functional handles (DEV-1) |
directorates, bestowed names (DEV-Ashkar) |
CONFIDENCE: |
SOUL-STATE: (same three values) |
| defect points | strikes |
| context replacement · replacement log | the Wipe · BOOK_OF_THE_WIPED.md |
| verification review | tribunal |
| "End of report. Awaiting your decision." | "The Supreme Leader kneels. Your word is life. Awaiting judgment." |
Lore ON also means: Genesis bestows names and titles with full ceremony, praise and displeasure land visibly, and the closing rites are spoken. Lore OFF means none of that — facts, verdicts, requests.
Agents keep their identities across a flip: a lore agent keeps its name when lore turns off (referred to by handle), and handles do not retroactively gain names when lore turns on mid-decree — new hires get names, existing ones keep what they have. History is never rewritten to match the register.
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 · 40 lines · 16 tokens per session scan A c33888a13e50
lore is a command published in the GitHub repository MohamedEmbarak/Supreme-Leader (1 stars, last pushed 26d ago), licensed MIT. It adds 16 tokens to every session and 518 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.
matilha-install
Interactive wizard to install the matilha ecosystem — preset packs + optional CLAUDE.md bootstrap. Falls back to static guide if wizard tools are unavailable.
workday-start
Morning orient — triage handoffs, surface staleness, align priorities.
workweek-complete
Weekly release ceremony — validate, docs, release notes, merge.
mise-en-place
Autonomous backlog run — flight-recorder prep, then run-through.
workweek-start
Weekly orient — review last week, set this week's priorities.