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 skills add wanshuiyin/ARIS-Movie-Director --skill comic-directorgit clone --depth 1 https://github.com/wanshuiyin/ARIS-Movie-DirectorWrote 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/skills/wanshuiyin/aris-movie-director/comic-director)<a href="https://agentmods.dev/skills/wanshuiyin/aris-movie-director/comic-director"><img src="https://agentmods.dev/badge/skills/wanshuiyin/aris-movie-director/comic-director/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/wanshuiyin/aris-movie-director/comic-director"><img src="https://agentmods.dev/badge/skills/wanshuiyin/aris-movie-director/comic-director.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 5.1 | $0.00000 | $0.03376 |
| Opus 5 | $0.00000 | $0.01688 |
| Sonnet 5 | $0.00000 | $0.00675 |
| Haiku 4.5 | $0.00000 | $0.00338 |
Grade A, and why
comic-director 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 12d 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 — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
comic-director — the Audited Spiral + Release (Phase 2/3)
The middle + right of Figure 1: take an authored comic.json (produced by the
comic-author skill, Phase 1) and turn it into baked frames + a clickable
viewer, through the audited spiral. Per frame: render a deterministic content-SVG blueprint → bake a
pixel-art frame (agent mcp__codex__codex sidecar) → a 3-reviewer cross-model panel_gate → keep / retry → page assembly →
projection. The movie twin of method-figure's render half. (Image-based today; video-based is next.)
Input contract — comic.json (authored upstream)
The contract boundary is comic.json + the assets it references (content-SVG blueprints, identity refs,
ART_BIBLE.md) — authored by comic-author. This skill is render + verify:
- It never invents a number or a cast — faithfulness is a deterministic token-diff over reviewers who never see the expected values; identity is judged against the ref the author supplied (cast-aware).
- It writes back only
image_path/active_attempt_id/wiki_node_id(+ the wiki trace) on KEEP. - The generator family (Codex image_gen) can NOT self-acquit. A KEEP needs the token-diff clean and the cross-model visual panel (Gemini + Codex) to pass. The calling agent (Claude) gives the final structural sign-off.
Full IR spec: ../../docs/comic-json.md /
../../schemas/comic.schema.json.
Run it (scripts/run_comic.py — agent-driven bake, CLI gates)
A pure-stdlib faithful port of packages/core/spiral_engine.js's movie branch. The cross-model gates
(Gemini + Codex vision) still shell the gemini / codex CLIs directly. The BAKE is performed by the
skill agent via the mcp__codex__codex MCP tool through --bake-mode=agent (the default): the core
emits a deterministic bake-request sidecar (prompt + absolute ref paths + exact out_path), the agent calls
mcp__codex__codex (sandbox: workspace-write, model: gpt-5.5, config: {model_reasoning_effort: xhigh, include_image_gen_tool: true},
cwd: <project>), and the core verifies the explicit out_path. (codex exec is RETIRED for real bakes — it
forced a hand-drawn SVG/struct+zlib fallback; --bake-mode=exec RAISES if it ever reaches a real bake. See
docs/spiral-runtime.md.)
python3 skills/comic-director/scripts/run_comic.py \
--project examples/comic_m3_audit --page P02_b08 --panels S12,S13,S14,S15 \
[--bake-lang zh] [--finalize] [--dry-run] [--skip-assembly] \
[--gemini-cmd "python3 cli/gemini_agy_shim.py"] [--gemini-family google]
--dry-runvalidates + prints each frame's concrete bake prompt (no image_gen) — run this first; it's also howcomic-authorconfirms Phase 1 is correct.--finalizerebuilds the single-file viewer (packages/viewer/build_comic.py) only if the run is shippable (nothing escalated/throttled/flagged-for-human; assembly accepted).--gemini-cmd(default: the legacygeminiCLI) — the argv prefix shelled for the google-family reviewer slot (the--model auto-gemini-3 -p <prompt>tail is appended). With the legacy CLI deprecated upstream (IneligibleTierError, 2026-07), pass--gemini-cmd "python3 cli/gemini_agy_shim.py"— the shipped shim translates the old interface to Antigravity'sagyand pins a Gemini model (Antigravity also serves Claude/GPT-OSS; the slot must stay google-family for cross-model quorum honesty).--gemini-family(defaultgoogle) — the provenance family recorded in the wiki for whatever--gemini-cmdactually routes to. It must stay non-openai(the visual quorum needs a second family); record honestly, never re-label.- Needs the
codexCLI + a google-family reviewer (legacygeminiCLI, or Antigravity via--gemini-cmd+ the shim) on PATH + headless Chrome (to rasterize the content-SVG blueprint). Reusesskills/method-figure/scripts/pickup_image.py.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 12d ago First seen · 139 lines · 0 tokens per session scan A befca4996d6d
comic-director is a skill published in the GitHub repository wanshuiyin/ARIS-Movie-Director (61 stars, last pushed 3d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,376 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 skills, from other repositories
creator-pipeline-supervisor
Orchestrate the entire AI film production — sequence the creative skills, manage shared project state, enforce continuity across character / location / costume / light / color / sound / edit, run QC, and produce the final delivery readiness report. Use when starting a new film project, recovering an existing one, or…
creator-character-designer
Design characters as integrated wholes — dramatic function, psychology, biography, visual identity, costume, props, casting profile, and FACS-coded expressions. Use when the user needs character development, character sheets, costume design, casting briefs, or AI-ready character references for an AI film project.
creator-final-cut-editor
Supervise the final assembly of AI-generated shots, audio, music, and graphics into a coherent finished film — rough cut, fine cut, final cut, AI-error triage, delivery formats. Use when AI material has been produced and needs to be assembled into a deliverable cut.
creator-prompt-engineer
Convert creative-department outputs (script, vision, cinematography, characters, sets, storyboards, shots) into producible, consistent AI image/video prompts — with tool-specific optimization, locked anchors, negative prompts, and safe alternatives. Default image tool priority for storyboard/character sheets is GPT…
creator-sound-music-designer
Design the film's sonic world — ambient atmosphere, foley, sound effects, silence as drama, score theme, character leitmotifs, scene-by-scene music plan, and AI sound/music prompts. Use when the user needs sound design, music vision, or AI audio prompts for an AI film.
creator-storyboard-artist
Translate scenes into storyboard panels — shot scales, angles, character blocking, movement direction, composition, and AI image/video prompts. Use when the user needs to visualize a scene panel by panel before production.