drive-after-effects

drive-after-effects is a skill for Claude Code, Codex from alphacornutum/layercake. It costs 168 tokens per session (3,207 once invoked), scanned A, original, MIT.

A set of instructions for safely inspecting and changing a live Adobe After Effects project through connected tools.

In plain words
What is it for?
Use it to inspect compositions and project items, make controlled project changes, and save an After Effects file.
Why use it?
It reduces mistakes when opening projects, identifying items, applying changes, and saving work in a shared editing session.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to inspect compositions and project items, make controlled project changes, and save an After Effects file.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/alphacornutum/layercake/drive-after-effects
Install

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.

Any agent
npx skills add alphacornutum/layercake --skill drive-after-effects
Clone the repo
git clone --depth 1 https://github.com/alphacornutum/layercake

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for drive-after-effects

README.md
[![agentmods](https://agentmods.dev/badge/skills/alphacornutum/layercake/drive-after-effects/github.svg)](https://agentmods.dev/skills/alphacornutum/layercake/drive-after-effects)
Your own site
<a href="https://agentmods.dev/skills/alphacornutum/layercake/drive-after-effects"><img src="https://agentmods.dev/badge/skills/alphacornutum/layercake/drive-after-effects/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.

agentmods 80×15 button for drive-after-effects

Your own site · 80×15
<a href="https://agentmods.dev/skills/alphacornutum/layercake/drive-after-effects"><img src="https://agentmods.dev/badge/skills/alphacornutum/layercake/drive-after-effects.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 168 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,207 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00168 $0.03207
Opus 5.5 $0.00067 $0.01283
Sonnet 5.5 $0.00034 $0.00641
Haiku 4.5 $0.00017 $0.00321

Measured 1mo ago against content hash 213edd995f0a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

drive-after-effects 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 1mo 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.

.ai/src/skills/drive-after-effects/SKILL.md · 79 lines

How it starts

The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Drive After Effects via MCP

Safe, id-correct workflow against the live AE GUI session.

Session assumption

LayerCake assumes a 1:1 agent ↔ After Effects session. There is no app-level lock. Concurrent agents or a human editing the same AE instance can race; stale fingerprint errors on patch/save are the only runtime detection.

Steps

  1. Check host — Call ae_host_status. If unavailable, fix platform config: macOS AE_APP_NAME and/or AE_EXECUTABLE (year suffix must match /Applications); Windows AE_EXECUTABLE pointing at AfterFX.exe.
  2. Open project — ae_open_project with an absolute .aep / .aet path when the needed project is not already open. If another project is open at a different path, open refuses (dirty or clean) — call ae_save_project / ae_close_project first. Never open over another project without an explicit close.
  3. Bind context — Call ae_project_context for the cheap fingerprint token (path, dirty, revision, fingerprint). Re-poll before every patch or save (or reuse a successful patch response fingerprint when no other mutator intervened).
  4. Project summary (when needed) — Call ae_project_summary for heavier health/portability orientation (third-party effects, missing footage/fonts). Prefer this before deep inventory when those concerns matter; skip for trivial single-layer edits. Do not use summary for fingerprint polling — that is ae_project_context.
  5. Inventory as needed — Prefer ae_list_comps (composition settings for set_comp_settings planning: dims/PAR/rate, integer duration/display-start/work-area frames, renderer, composition switches; plus layer switches, parent/matte ids, integer frame timing, Solid source.footageKind), ae_list_sources, and/or ae_list_folders before writing custom scripts. For cleanup planning, call ae_get_item_refs — when unknownRefsPossible is true, do not treat the item as safe to delete. Panel ops need real Item.id handles from inventory (including rootFolder.id — never a magic 0).
  6. Docs when unsure — ae_docs_search → ae_docs_get (or ae://docs/...) before inventing DOM APIs.
  7. Optional backup / copy-first — Before risky or broad patches, ae_save_project with mode: "create_backup" and the current fingerprint (requires a clean, saved project; dirty projects must use save_copy instead). Agents MAY save_copy (or otherwise work on a copy) before mutating when the original project file must remain pristine. create_backup copies the .aep only — it does not collect linked footage (not Collect Files).
  8. Typed patch — Prefer ae_patch_project (apply-only) over raw eval for: set_text_style (partial TextDocument style bag — font, size, leading/autoLeading, fill/stroke, justification, text, box geometry, allCaps/smallCaps, …; omit key = preserve; plan via ae_get_layer SourceText projection on extended/full; evidence is authored style/fonts plus optional evaluatedStyle/evaluatedFonts; post-condition on authored supplied keys only; fingerprint guards only — no expected-current bag; does not clear Source Text expressions), create_text (comps-only target + layout point|box + text; box requires boxTextSize; optional name / style same allowlist as set_text_style; always new Layer.id), rename_layer, rename_project_item, set_layer_index, create_solid (optional name), replace_layer_source, set_layer_timing (integer frames; not remapping; verified keyframe preservation — see Gotchas for source slip vs drag), set_layer_switches (timeline/layer switches — supply only keys to change in switches; omitted switches and non-switch state are preserved; evidence is a full switch snapshot before/after; use this for timeRemapEnabled, mute-video / keep-audio, solo/shy/locked, etc.), set_comp_settings (comps-only target.compId XOR compName + partial settings bag; omit key = preserve; optional nested settings.switches; integer-frame evidence; duration shrink clamps work area unless explicit work area would overrun — that fails; place before set_layer_timing in mixed batches, especially when changing frameRate), set_property_expression (build segment paths from nested ae_get_layer tree — effect params need parade → effect instance → param; nexrender propertyPath with . / -> is an alternative — exactly one selector), set_layer_transform (authored 2D Transform — supply only keys to change in nested transform bag; omit=preserve; evidence is actual authored/pre-expression numeric before/after snapshots; prefer over eval for slot repair after replace_layer_source, e.g. set Position to the new Anchor Point; no op-level expected-current bag — use matching project.fingerprint), reset_layer_surface (resetTransforms applies/verifies AE defaults with value evidence, not a transforms boolean; typically Position at composition center — not “match new Anchor”; clearExpressions is separate), delete_layer, panel create_folder (optional name) / move_project_item, and guarded cleanup via safe_delete_project_item. Pass project.path + project.fingerprint guards. All layer-targeting patch ops accept id or unique name with the same ambiguity rules as ae_get_layer (no ids-only exceptions). Prefer stable ids when names may collide. For ae_get_layer extended/full, Transform and SourceText may include authoredValue / evaluatedValue — wrapper purity MUST use authored/pre-expression samples, not post-expression alone. SourceText is projected as { kind: "textDocument", style, boxText?, pointText? }. safe_delete_project_item refuses in-use / unknownRefsPossible and empty-folder-only (non-recursive); delete_project_item remains AE-permissive (recursive folders; in-use allowed) — prefer safe delete + ae_get_item_refs for cleanup. Cover/Contain expression bodies, protected control-layer name policy, render-backed visibility, and main/config reachability stay agent/domain concerns — LayerCake does not enforce them. On success, reuse the returned fingerprint when no other mutator intervened; otherwise re-bind context.
  9. Persist — ae_save_project with mode: "save_copy" (and an absolute destination) when you want changes on disk. Patch never saves implicitly.
  10. Eval escape hatch — ae_eval_script bypasses typed safety and fingerprint guards. Use only for one-offs the patch vocabulary cannot express. After Effects is an ES3-like dialect — read references/extendscript.md (MCP: skill://drive-after-effects/references/extendscript.md) before writing scripts (var / function / for; not const, arrows, or Array.map). That reference also covers the wrap return contract (top-level return for payloads; empty success is normal for void scripts; bare IIFE inner-return is a footgun). Look up targets by id:

Read the full file on GitHub · 79 lines

Files

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.

Changes

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.

  1. 1mo ago Changed · +1 lines 213edd995f0a
  2. 2mo ago First seen · 78 lines · 168 tokens per session scan A 13f464dbfc6a

Subscribe to this mod's changes

drive-after-effects is a skill published in the GitHub repository alphacornutum/layercake (0 stars, last pushed 20d ago), licensed MIT. It adds 168 tokens to every session and 3,207 once invoked, about $0.0007 per session on Opus 5.5. 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.

Related

drive-after-effects compared with skills from other repositories

drive-after-effects next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
drive-after-effectsalphacornutum/layercakeSkill020d agoMITA168Claude Code, Codex
after-effects-scriptingMaciejdziuba/youtube-skillsSkill42mo agoMITA148Claude Code, Codex
vox-directorAlisa0808/vox-directorSkill2.7k1mo agoMITA236Claude Code, Codex
style-guideEngine-Room-Games/after-effects-mcpSkill48yesterdayMITA74Claude Code
flueSFKislev/FlueSkill10421d agoMITA36Claude Code, Codex
saas-product-demo-videonoamdorr/saas-product-demo-videoSkill69yesterdayMITA130Claude Code
after-effectsEngine-Room-Games/after-effects-mcpSkill48yesterdayMITA89Claude Code