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/byungjunjang/slide-master/agents-mdgit clone --depth 1 https://github.com/byungjunjang/slide-masterWrote 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/byungjunjang/slide-master/agents-md)<a href="https://agentmods.dev/instructions/byungjunjang/slide-master/agents-md"><img src="https://agentmods.dev/badge/instructions/byungjunjang/slide-master/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 | $0.01354 | $0.01354 |
| Opus 5 | $0.00677 | $0.00677 |
| Sonnet 5 | $0.00271 | $0.00271 |
| Haiku 4.5 | $0.00135 | $0.00135 |
Grade A, and why
slide-master 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 5d 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 — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — Codex execution rules for slide-master
This repo is dual-host: Claude Code and Codex. CLAUDE.md owns
standing repository conventions. Route selection belongs to
.claude/skills/ppt-master/workflows/routing.md.
After routing, the selected skill or workflow owns execution and gates. The rules
below add Codex-side enforcement; they never override the selected owner.
Skill source (generated pointer stubs)
.claude/skills/is canonical (ppt-master,ppt-template-fill,native-enhance-pptx,diagram-design,codex-image)..codex/skills/holds generated discovery stubs — samename/descriptionfrontmatter plus a redirect body — regenerated bypython3 .claude/skills/ppt-master/scripts/sync_codex_stubs.py.- Never hand-edit
.codex/skills/. Edit the.claudetree, then re-run the sync script.preflight.pyhard-fails when stubs are stale. - Before reading any full presentation skill or workflow, read the routing dispatcher and select the route. Then read only the selected canonical owner(s) in full. A broad presentation discovery signal does not authorize preloading the main SVG skill for a direct-PPTX route.
- Path resolution:
${SKILL_DIR}and bare relative paths (references/...,workflows/...,scripts/...,templates/...) resolve against the canonical skill directory. Run all commands from the repository root. Ifpython3is missing (common on Windows), rerun the same command withpython.
PPT requests — MANDATORY procedure
When the user asks for a presentation ("PPT 만들어줘", "make slides", "生成PPT", a deck from a document/topic/template):
- Route before full-load. Read
.claude/skills/ppt-master/workflows/routing.mdfirst. Use its one discriminator question only for the ambiguity it defines; do not load competing full owners before the answer. - Load the selected owner(s) in full. The router owns the complete matrix; this table is a compact Codex handoff summary:
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.
- 5d ago First seen · 88 lines · 1,354 tokens per session scan A 5f92682d9e94
slide-master AGENTS.md is an instructions file published in the GitHub repository byungjunjang/slide-master (216 stars, last pushed 1mo ago), licensed MIT. It adds 1,354 tokens to every session, about $0.0068 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 2026-08-30.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.