Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/wanshuiyin/ARIS-Movie-Directornpx agentmods add skills/wanshuiyin/aris-movie-director/comic-asset-review-loopWrote 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-asset-review-loop)<a href="https://agentmods.dev/skills/wanshuiyin/aris-movie-director/comic-asset-review-loop"><img src="https://agentmods.dev/badge/skills/wanshuiyin/aris-movie-director/comic-asset-review-loop/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-asset-review-loop"><img src="https://agentmods.dev/badge/skills/wanshuiyin/aris-movie-director/comic-asset-review-loop.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 | $0.00275 | $0.11156 |
| Opus 5 | $0.00138 | $0.05578 |
| Sonnet 5 | $0.00055 | $0.02231 |
| Haiku 4.5 | $0.00028 | $0.01116 |
Grade A, and why
comic-asset-review-loop 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 — 451 lines — stays where its author put it; the contents beside it link to each section on GitHub.
comic-asset-review-loop — the UPSTREAM ref gate (Phase 1 · S5)
The ref gate the comic side was missing. comic-director's panel_gate reviews composed output; the
assembly_gate reviews cross-panel consistency. Neither gates the identity refs that feed both — so
without this skill, identity drift is only caught downstream, after credits are spent on a panel bake. This
skill is the Layer-2 gate on a SINGLE reusable reference asset (the character sheets / location plates /
prop cutouts the ART_BIBLE.md points every bake at), run before any panel composition.
A reusable asset is a one-way door: once a hundred panels condition on duo_canonical_ref_v001.png, you cannot
quietly swap it. So the lock must be earned cross-model, never self-certified by the generator. This skill
locks an asset only at 准×3 — Claude and Gemini and Codex each independently pass the same review
round — or it sends the asset back to be regenerated, or (at the round ceiling) escalates the asset
requirement itself back to the outline/storyboard layer. The executor (and the generation model family)
never acquit their own ref.
Pipeline position (the Phase-1 asset DAG — the documented contract): this lock runs AFTER the
human-approved outline (OUTLINE_DRAFT_VALID only requires every referenced asset to be DECLARED with a
complete, generatable request — never pre-locked assets) and the provisional storyboard's
consolidated_asset_requests, and BEFORE OUTLINE_FINAL_LOCK (cheap re-check that the locked assets still
match the approved outline) → storyboard FINAL asset-resolution validation → blueprint authoring, where the
hard locked-asset barrier sits. (The old single-stage contract — outline gate demanding locked assets —
deadlocked and is retired.)
asset (review_status:"pending") ◀── comic-asset-ref-generator (S4: generates, NEVER self-locks)
│
▼
LAYER 1 — STATIC CI GATE (deterministic, zero credits)
check_asset_collisions.py (one canonical owner per filename — "one visual dialect, never two")
+ build asserts: zero-text contract · literal contract · raster-ref 6-field completeness
│ pass
▼
LAYER 2 — VISUAL LOOP (round R = 1 … MAX_REVIEW_ROUNDS=3)
① Claude narrative ‖ ② Gemini visual (primary: identity/iso) ‖ ③ Codex synth (policy/semantic)
each reads the REAL asset file · scores 5 dims (0–5 ints) · flags failure_modes from the fixed vocab
│
▼ Codex synthesises: MIN-fuse per dim (max for inverted) · threshold · per-reviewer unanimity
准×3 ? ── no, a family HARD-FAILS a floor ─▶ comic-asset-ref-generator --regenerate (bump version) ─▶ ① R+1
│ no, third family just ABSENT (e.g. Gemini down) ─▶ re-VOTE (re-collect the missing reviewer; NO re-bake)
│ no (safety_ip<3) ─▶ HARD abandon_shot (IP veto, no retries)
│ no (R == MAX_REVIEW_ROUNDS) ─▶ ESCALATE the asset REQUIREMENT to outline/storyboard (abandon_shot)
│ yes
▼
LOCK — asset.status=locked + payload.review_status=locked (ONE-WAY DOOR, immutable for the rest of Phase 1)
+ score_progression audit table (ASSET_REVIEW.md) + decision/review/failure_mode wiki nodes + edges
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 · 451 lines · 275 tokens per session scan A bdb5a9f044df
comic-asset-review-loop is a skill published in the GitHub repository wanshuiyin/ARIS-Movie-Director (61 stars, last pushed 3d ago), licensed MIT. It adds 275 tokens to every session and 11,156 once invoked, about $0.0014 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 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.