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/tph-kds/deckforge/agents-mdgit clone --depth 1 https://github.com/tph-kds/deckforgeWhat 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 | $0.00498 | $0.00498 |
| Opus 5 | $0.00249 | $0.00249 |
| Sonnet 5 | $0.00100 | $0.00100 |
| Haiku 4.5 | $0.00050 | $0.00050 |
Grade A, and why
deckforge 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 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.
How it starts
The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DeckForge Agent Entry Point
This repository contains Agent Skills and reference scaffolds for reliable editable, browser-native slide applications.
Code intelligence
Prefer Serena semantic tools for source-code navigation, symbol lookup, references, implementations, dependency tracing, and symbol-level refactoring.
Use built-in read/grep tools for configuration files, documentation, logs, plain-text searches, or when Serena cannot resolve the required code context.
Read order
rules/README.mdrules/repository-boundaries.mdrules/design-quality.mdrules/security-rules.md- the relevant
skills/*/SKILL.md skills/deckforge/references/delivery-acceptance-contract.mdfor implementation work
Default routing
- Use
skills/deckforge/SKILL.mdfor creating, redesigning, extending, or migrating a presentation product. - Use
skills/deckforge-audit/SKILL.mdfor review-only work. - Use
skills/deckforge-runtime-planner/SKILL.mdfor architecture planning without implementation. - Use
skills/deckforge-publish/SKILL.mdfor publishing, embedding, and delivery. - Use
skills/deckforge-visual-evidence/SKILL.mdfor browser-based verification of a generated application and for producing executed capability evidence. - Use
skills/deckforge-skill-evaluator/SKILL.mdfor comparing skill conditions and gatekeeping skill releases.
For ordinary end-user requests to create slides, select the editable-deck profile unless the user explicitly asks for a presenter-only artifact.
Non-negotiable implementation rules
- Use semantic layout slots rather than arbitrary coordinates by default.
- Do not claim an editor exists unless controls mutate DeckProject state and changes persist.
- Keep the editor and presenter as separate surfaces.
- Provide visible shortcut guidance.
- Run schema, layout, output-contract, build, and behavioral checks before completion.
Plugin discovery
.agents/plugins/marketplace.json.claude-plugin/plugin.json.codex-plugin/plugin.json
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 · 60 lines · 498 tokens per session scan A 41da07c17bb5
deckforge AGENTS.md is an instructions file published in the GitHub repository tph-kds/deckforge (4 stars, last pushed 15d ago), licensed MIT. It adds 498 tokens to every session, about $0.0025 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
agents-universe CLAUDE.md
Instructions for agents-universe/agents-universe, covering agents universe — enterprise ai agent framework, project overview, monorepo layout, development commands and api (from packages/api/).
gastown-gui CLAUDE.md
Instructions for web3dev1337/gastown-gui, covering claude.md - gas town gui, read these entire documents before doing anything, architecture, file size discipline and commands.
nanobrowser CLAUDE.md
Instructions for nanobrowser/nanobrowser, covering claude.md, project overview, development commands, workspace tips and architecture.
browser-control AGENTS.md
Instructions for keon/browser-control: Use this project as a tiny browser pipe, not an agent framework.
nuwax AGENTS.md
Instructions for nuwax-ai/nuwax, covering ai agent system documentation, 系统概述, ai agent 架构, 核心组件 and ai 功能特性.
sprawling CLAUDE.md
Instructions for 2youg1/sprawling: See AGENTS.md. It is the whole instruction set for this repository — the loop, what to read first, the five steps of one change, the rules a machine holds, and the language and commit conventions.