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 skills/tph-kds/deckforge/deckforge-auditnpx skills add tph-kds/deckforge --skill deckforge-auditgit 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 | $0.00055 | $0.00373 |
| Opus 5 | $0.00028 | $0.00187 |
| Sonnet 5 | $0.00011 | $0.00075 |
| Haiku 4.5 | $0.00006 | $0.00037 |
Grade A, and why
deckforge-audit 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.
What it actually says
DeckForge Audit
Read ../deckforge/system-prompt.md, ../deckforge/built-in-skills/quality-gate.md, and ../deckforge/assets/quality-rubric.json before reviewing the target.
Inspect the repository structure, deck model, semantic layout bindings, renderer, editor commands, persistence, presenter state, styles, routes, and tests. Run ../deckforge/scripts/audit_deck_layout.py against representative DeckProject files and ../deckforge/scripts/validate_output_contract.py against the generated application using its declared delivery profile. Run the application when possible and review every representative slide at the canonical 16:9 viewport plus a narrow viewport. Exercise keyboard navigation, touch behavior, builds, overview, notes, fullscreen, reduced motion, focus order, and embed mode when those capabilities exist.
Report evidence by route, component, slide, viewport, and interaction. Separate findings into blocking defects, high-impact improvements, and optional polish. For each issue, explain the consequence and a concrete remediation. Detect unsupported claims, invented metrics, generic AI aesthetics, repeated layouts, weak narrative rhythm, overflow, inaccessible controls, and editor chrome leaking into the audience surface.
Do not edit the project unless explicitly asked. Do not claim visual, accessibility, performance, or keyboard checks were run when the relevant preview or tooling was unavailable.
Treat missing required editor behavior, decorative-only controls, unresolved layout slots, collisions, unsafe margins, missing shortcut guidance, and persistence failures as blocking defects.
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 · 19 lines · 55 tokens per session scan A c9d64ca2efc6
deckforge-audit is a skill published in the GitHub repository tph-kds/deckforge (4 stars, last pushed 16d ago), licensed MIT. It adds 55 tokens to every session and 373 once invoked, about $0.0003 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 skills, from other repositories
ppt-generation
Use this skill when the user requests to generate, create, or make presentations (PPT/PPTX). Creates visually rich slides by generating images for each slide and composing them into a PowerPoint file.
image-generation
Use this skill when the user requests to generate, create, imagine, or visualize images including characters, scenes, products, or any visual content. Supports structured prompts and reference images for guided generation.
podcast-generation
Use this skill when the user requests to generate, create, or produce podcasts from text content. Converts written content into a two-host conversational podcast audio format with natural dialogue.
video-generation
Use this skill when the user requests to generate, create, or imagine videos. Supports structured prompts and reference image for guided generation.
music-generation
Use this skill when the user requests to generate, create, compose, or produce music or songs — background music, theme songs, jingles, or instrumental tracks. Generates a song from a style/mood prompt and optional lyrics via the MiniMax music API.
surprise-me
Create a delightful, unexpected "wow" experience for the user by dynamically discovering and creatively combining other enabled skills. Triggers when the user says "surprise me" or any request expressing a desire for an unexpected creative showcase. Also triggers when the user is bored, wants inspiration, or asks for…