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.
git clone --depth 1 https://github.com/MigueDuque/capcut-mcp-server-extendedWrote 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/commands/migueduque/capcut-mcp-server-extended/edit_draft)<a href="https://agentmods.dev/commands/migueduque/capcut-mcp-server-extended/edit_draft"><img src="https://agentmods.dev/badge/commands/migueduque/capcut-mcp-server-extended/edit_draft/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/commands/migueduque/capcut-mcp-server-extended/edit_draft"><img src="https://agentmods.dev/badge/commands/migueduque/capcut-mcp-server-extended/edit_draft.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00000 | $0.00999 |
| Opus 5.5 | $0.00000 | $0.00400 |
| Sonnet 5.5 | $0.00000 | $0.00200 |
| Haiku 4.5 | $0.00000 | $0.00100 |
Grade A, and why
edit_draft 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 2mo 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 — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Edita un proyecto CapCut existente agregando subtítulos al PROYECTO ORIGINAL.
Parámetros
Solicita los que no haya proporcionado:
- draft_path (requerido): ruta a la carpeta del draft
- typography_style (opcional, default: defaultTypeWhite): defaultTypeWhite | defaultTypeBlack | defaultTypeRed
- animation_in (opcional, default: popInUpper): popInUpper | ninguna
- position_y (opcional, default: -0.4): Y del subtítulo en coordenadas transform; -1=fondo, 0=centro, 1=tope
- position_x (opcional, default: 0.0): X del subtítulo; -1=izquierda, 0=centro, 1=derecha
- screen_type (opcional, default: mobile): mobile → 1080×1920 desktop → 1920×1080 custom → preguntar screen_width y screen_height
- whisper_model (opcional, default: base): tiny | base | small | medium | large
- confirm_transcription (opcional, default: true)
- fade_duration (opcional, default: 0.2): duración del fade de entrada en segundos. 0.167 = 5 frames a 30fps (rápido, ideal subtítulos), 0.4 = medio, 1.5 = lento
- align (opcional, default: center): alineación horizontal de las palabras — left | center
Variables
PYTHON=/c/Users/Migue/AppData/Local/Programs/Python/Python311/python
TMP_DIR=C:/smart_cut/tmp
WORDS_TMP={TMP_DIR}/capcut_words_$$.json
DRAFT_JSON={draft_path}/draft_content.json
# Resolución según screen_type
screen_type=mobile → SCREEN_WIDTH=1080 SCREEN_HEIGHT=1920
screen_type=desktop → SCREEN_WIDTH=1920 SCREEN_HEIGHT=1080
screen_type=custom → preguntar al usuario
Pasos
Paso 0 — Crear directorio temporal
mkdir -p "{TMP_DIR}"
(No usar /tmp ni C:/Windows/Temp — solo C:/smart_cut/tmp)
Paso 1 — Inspeccionar + validar (en paralelo)
PYTHONUTF8=1 {PYTHON} utils_py/inspect_draft.py "{DRAFT_JSON}"
PYTHONUTF8=1 {PYTHON} utils_py/validate_project.py "{DRAFT_JSON}"
Extrae audio_path, duration_sec, fps. Abortar si valid: false o no hay audio.
Paso 2 — Transcribir
PYTHONUTF8=1 {PYTHON} utils_py/transcribe_audio.py "{audio_path}" \
--lang es --model {whisper_model} > {WORDS_TMP}
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.
- 2mo ago First seen · 108 lines · 0 tokens per session scan A 243c62737a51
edit_draft is a command published in the GitHub repository MigueDuque/capcut-mcp-server-extended (14 stars, last pushed 7mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 999 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 2026-08-31.
edit_draft compared with commands from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| edit_draftMigueDuque/capcut-mcp-server-extended | Command | 14 | 7mo ago | MIT | A | 0 | Claude Code |
| checklistgithub/spec-kit | Command | 148k | yesterday | MIT | A | 13 | Claude Code |
| clarifygithub/spec-kit | Command | 148k | yesterday | MIT | A | 27 | Claude Code |
| specifygithub/spec-kit | Command | 148k | yesterday | MIT | A | 13 | Claude Code |
| analyzegithub/spec-kit | Command | 148k | yesterday | MIT | A | 26 | Claude Code |
| convergegithub/spec-kit | Command | 148k | yesterday | MIT | A | 35 | Claude Code |
| implementgithub/spec-kit | Command | 148k | yesterday | MIT | A | 14 | Claude Code |