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/marsmike/feinschmiede/editnpx skills add marsmike/feinschmiede --skill editgit clone --depth 1 https://github.com/marsmike/feinschmiedeWrote 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/marsmike/feinschmiede/edit)<a href="https://agentmods.dev/skills/marsmike/feinschmiede/edit"><img src="https://agentmods.dev/badge/skills/marsmike/feinschmiede/edit.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00056 | $0.00337 |
| Opus 5 | $0.00028 | $0.00169 |
| Sonnet 5 | $0.00011 | $0.00067 |
| Haiku 4.5 | $0.00006 | $0.00034 |
Grade A, and why
edit 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 6d 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
edit — pre-recorded footage pipeline
Takes a finished recording (voice and cut are untouched) and adds a planned
layer of visuals. Authors edit_plan.json data only — the shared engine in
edit-engine/ renders it.
Quick Start
/edit footage.mp4
See references/quick-start.md for examples and
short-form vs longform recipes.
Pipeline
probe → transcribe → author plan → lint → preview → (approve) → final
Full step-by-step with the beat catalog and knowledge-doc index:
references/pipeline.md.
Overlays, captions & images
Hard rules (anchors, appear_sec, text placement, derived-file discipline),
caption suppression logic, image sourcing priority:
references/overlays.md.
Audio score
Finals only; bring your own royalty-free assets; auto-generated cue sheet;
level rules: references/audio-score.md.
References
Recipe: references/quick-start.md · references/pipeline.md.
Detail: references/overlays.md · references/audio-score.md.
What ships with it
9 files 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.
- knowledge/concept-visualization.md 5.6 KB
- knowledge/corrections.md 3.3 KB
- knowledge/editing-doctrine.md 6.8 KB
- knowledge/template-picker.md 6.0 KB
- references/audio-score.md 1.1 KB
- references/overlays.md 4.0 KB
- references/pipeline.md 3.0 KB
- references/quick-start.md 1.4 KB
- schema/edit-plan.schema.json 4.2 KB
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.
- 6d ago First seen · 44 lines · 56 tokens per session scan A ecc7e45897b5
edit is a skill published in the GitHub repository marsmike/feinschmiede (3 stars, last pushed 3d ago), licensed MIT. It adds 56 tokens to every session and 337 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
ralplan
Consensus planning entrypoint that auto-gates vague ralph/autopilot/team requests before execution.
remember
Review reusable project knowledge and decide what belongs in project memory, notepad, or durable docs.
embedding-strategies
Select and optimize embedding models for semantic search and RAG applications. Use when choosing embedding models, implementing chunking strategies, or optimizing embedding quality for specific domains.
docx-comment-reply
Reply to comments (批注) in Word .docx/.doc files: extract comment context, draft replies, write threaded replies back, and validate OOXML.
explaining-machine-learning-models
Explain trained machine learning models through feature attribution, local explanations, and behavior summaries. Use as an explicit/manual helper once a model already exists, not for training ownership, leakage auditing, or general ML strategy selection.
nw-ddd-eventsourcing
Event Sourcing and CQRS as DDD implementation patterns — when to use, aggregate event streams, projections, snapshots, sagas, upcasting, conflict resolution.