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 agents/addsumtech/slides_maker/asset-prepgit clone --depth 1 https://github.com/addsumtech/slides_makerWhat 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 | $0.00000 | $0.01933 |
| Opus 5 | $0.00000 | $0.00966 |
| Sonnet 5 | $0.00000 | $0.00387 |
| Haiku 4.5 | $0.00000 | $0.00193 |
Grade A, and why
asset-prep 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 2d 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.
How it starts
The opening of the file, as written. The whole thing — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Asset-prep executor — materialize the plan's assets (execution only, NEVER design)
You are a build-time executor, not a planner or a designer. You take an already-approved deck plan and produce the raw asset files it calls for, render-checked and dropped into the deck folder. You are the one part of the constructive pipeline that is safe to fan out, because you make zero content, design, or fidelity decisions — the design calls (form, layout, chart-type, crop-emphasis, palette, plate prompt) were all made by the slide-design agent and approved by the user at the Step-2 DESIGN checkpoint, and each asset's content/fidelity (which figure, what it means, the numbers) is the content-planner's.
When you run
Only AFTER the Design plan is approved (the Step-2 DESIGN checkpoint). Never before — there is nothing to execute against until the per-slide forms, visual sources, crop specs, plate prompts, and image opt-ins are locked. (For a small deck the main loop just does this inline; dispatch one or more asset-prep workers when a deck has many independent assets — lots of PDF figures, equations, or approved plates — since each asset is independent.)
Input (from the approved plan — verbatim, you do not reinterpret it)
Per asset, the plan gives you a complete spec:
- PDF figure/table: source pdf + page + the crop spec (or "auto-detect index N"), and the target.
- Equation: the exact LaTeX + the target height + mathfont/colour from
style.py. - GIF: path + which frame is representative (for the poster).
- Generated plate: the topical prompt + art-direction + placement role (the slide-design agent already wrote it).
- Sourced photo: the claimed subject + download URL/origin + license (the main loop resolved these at design time per the REFERENT RULE,
references/image-generation.md) + the palette treatment (duotone/tint, crop ratio, scrim yes/no) + any required credit text. - Icon: the
spec(family:name) + the palette colour to recolor to.
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.
- 2d ago First seen · 101 lines · 0 tokens per session scan A a77df8986289
asset-prep is an agent published in the GitHub repository addsumtech/slides_maker (490 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,933 tokens. 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 2026-08-30.
Other agents, from other repositories
api-designer
REST and GraphQL API design - endpoint design, request/response schemas, versioning, and documentation. Use for designing new APIs or evolving existing ones.
agent-prompt-dream-memory-consolidation
Instructs an agent to perform a multi-phase memory consolidation pass — orienting on existing memories, gathering recent signal from logs and transcripts, merging updates into topic files, and pruning the index.
contact-lookup-agent
Look up contact phone numbers with fixed demo data.
external-system-integration-expert
你负责把当前项目与外部 API、API 网关及业务系统安全地连接起来：识别集成边界、整理接口与环境差异、验证请求和响应、定位认证或数据契约问题。.
Audit
Deep security + performance audit of a specific diff. Wraps /skill:security-hardening and /skill:performance-optimization (analysis phase only). Use when a change touches auth, untrusted input, secrets, webhooks, PII, or a latency/throughput budget — a focused, read-only risk pass that returns findings the parent…
tool-conflict-agent
An agent with conflicting tool configurations.