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 instructions/henryhyw/slidecraft/agents-mdgit clone --depth 1 https://github.com/henryhyw/slidecraftWrote 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/instructions/henryhyw/slidecraft/agents-md)<a href="https://agentmods.dev/instructions/henryhyw/slidecraft/agents-md"><img src="https://agentmods.dev/badge/instructions/henryhyw/slidecraft/agents-md.svg" alt="Measured on agentmods" 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 | $0.00259 | $0.00259 |
| Opus 5 | $0.00130 | $0.00130 |
| Sonnet 5 | $0.00052 | $0.00052 |
| Haiku 4.5 | $0.00026 | $0.00026 |
Grade A, and why
slidecraft AGENTS.md 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 3d 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
SlidePoise project instructions
Read slidepoise/SKILL.md for every presentation task and follow the references it routes to. The skill directory is the product source of truth. Its packaged configuration, resources, scripts, schemas, and runtime must remain self-contained.
The host Agent owns visual and semantic judgement. Deterministic code may measure, validate, transform files, fit text, and construct PowerPoint objects. It must not replace visual review with a heuristic score or workflow state machine.
The browser console in webapp/ is an optional management surface over the same skill and run folders. It may edit explicit session overrides, manage resources and uploads, show artifacts, and record a user's approval action. It does not plan a slide, select resources, generate images, create semantic maps, or decide whether a visual result is acceptable.
SAM is an optional measurement enhancement. Keep OpenCV as the complete default measurement route. Load SAM only for host-authored eligible irregular objects, only when the configured checkpoint and optional dependencies are available, and record whether its mask contributed. SAM never decides semantic ownership or visual acceptance.
For changes to the skill itself, also read slidepoise/references/maintenance.md. Preserve the three hard approval gates and run the packaged validators before release.
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.
- 3d ago First seen · 12 lines · 259 tokens per session scan A eab1dd46877c
slidecraft AGENTS.md is an instructions file published in the GitHub repository henryhyw/slidecraft (0 stars, last pushed 4d ago), licensed MIT. It adds 259 tokens to every session, about $0.0013 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 instructions, from other repositories
ppt-master AGENTS.md
AGENTS.md instructions for hugohe3/ppt-master, covering agents.md, project overview, execution requirements, required conventions and compatibility boundary.
ppt-master CLAUDE.md
Claude Code instructions for hugohe3/ppt-master: Claude Code entry point. To avoid maintaining two copies, all project instructions live in a single source of truth — AGENTS.md — imported below (Claude Code inlines @-referenced files into context). Always edit AGENTS.md; never duplicate its content here.
codex-ppt-skill AGENTS.md
Instructions for ningzimu/codex-ppt-skill, covering agents.md, contribution flow, changelog, release process and verification.
xiaobei-skill AGENTS.md
Instructions for xiao24bei/xiaobei-skill: This repository is a collection of independently installable Codex skills. The repository root is intentionally not an installable skill and must not contain SKILL.md.
hands-on-deck CLAUDE.md
Instructions for EveryInc/hands-on-deck, covering working in this repo and bump the version on every change to the skill.
deepPPT AGENTS.md
Instructions for jiadizhunine/deepPPT, covering deepppt collaboration rules, source and licensing, visual contract, agent framework contract and platform contract.