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.
npx agentmods add commands/localplugins/plugins/multiplygit clone --depth 1 https://github.com/localplugins/pluginsWhat 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 | $0.00018 | $0.00517 |
| Opus 5 | $0.00009 | $0.00259 |
| Sonnet 5 | $0.00004 | $0.00103 |
| Haiku 4.5 | $0.00002 | $0.00052 |
Grade A, and why
multiply 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 yesterday.
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
Multiply
Turn a single source into a full set of on-brand, channel-specific derivatives. Reads only what the user provides; writes files; never posts anything.
Arguments: $ARGUMENTS
Workflow
- Parse args. Identify the source (a file path or inline text), and optional flags:
--channels(default: linkedin, x-thread, newsletter, instagram, short-video),--brand <name>(default brand),--locales xx-XX,...(default: none). - Load the brand profile using the
brand-voiceskill (fromcontent/brand/or the named brand). If none exists, suggest/brand-setupand offer sensible defaults. - Plan. Delegate to the
strategistsubagent with the source + selected channels. It returns a derivative plan (channel × angle × persona × key message). - Confirm the plan with the user. Show the plan and ask them to approve, trim, or adjust before drafting. Do NOT generate everything unprompted.
- Draft each derivative. For each approved row, apply the
channel-formatsskill (that channel's spec) plus thebrand-voiceskill to write the asset. - Localize (if
--localesset). For each target locale, apply thetranscreationskill to adapt selected assets to that market. - Guard. Delegate all drafts to the
brand-guardiansubagent. Apply its corrections; if anything isfix, revise and re-check. - Write output. Create
content/output/<campaign-slug>/(slug from the source title + a short suffix). Write one file per asset:<channel>.md, and<locale>/<channel>.mdfor localized versions. - Write
index.mdin that folder: a dashboard tableAsset | Channel | Locale | Persona | Chars | Compliance | Notes, one row per file, plus a one-line summary and next-steps (copy/paste or schedule).
Output is copy-paste / schedule-ready. Never auto-post. Never access the network.
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.
- yesterday First seen · 26 lines · 18 tokens per session scan A 9075ad9a59b2
multiply is a command published in the GitHub repository localplugins/plugins (5 stars, last pushed 1mo ago), licensed MIT. It adds 18 tokens to every session and 517 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
security-audit-static
Static security audit of AI-built code — map trust boundaries, cross-reference documented intent, self-refute every finding, and report only evidence-backed risks.
performance-audit-static
Static performance audit of AI-built code — find N+1 queries and request waterfalls, over-fetching, missing indexes, and caching opportunities, ranked by effort and impact.
document-app
Reverse-engineer an AI-built codebase into the system documents reviewers and auditors need — a core set (architecture, flows, permissions, variables) plus conditional docs (emails, cron, SEO, automation) when they apply.
analyze-test
Analyze A/B test results — statistical significance, sample size validation, and ship/extend/stop recommendations.
plan-okrs
Brainstorm team-level OKRs aligned with company objectives — qualitative objectives with measurable key results.
write-stories
Break a feature into backlog items — user stories, job stories, or WWA format with acceptance criteria.