Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add big-emotion/agent-atelier/plugin install agent-commsWrote 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/big-emotion/agent-atelier/bigemotion-reel-clip)<a href="https://agentmods.dev/skills/big-emotion/agent-atelier/bigemotion-reel-clip"><img src="https://agentmods.dev/badge/skills/big-emotion/agent-atelier/bigemotion-reel-clip/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/big-emotion/agent-atelier/bigemotion-reel-clip"><img src="https://agentmods.dev/badge/skills/big-emotion/agent-atelier/bigemotion-reel-clip.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 | $0.00150 | $0.02220 |
| Opus 5.5 | $0.00060 | $0.00888 |
| Sonnet 5.5 | $0.00030 | $0.00444 |
| Haiku 4.5 | $0.00015 | $0.00222 |
Grade A, and why
bigemotion-reel-clip 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 today.
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 — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.
BIG EMOTION reel clip
The operator hands over a video and an instruction; this skill delivers the whole publication folder, then opens the clip for review. Respond to the operator in French; this file stays English.
Adapted from EthniAfrica's ethniafrica-reel-clip (October 2026). What differs,
by decision of 14 October 2026:
- One surface: LinkedIn, posted from the BIG EMOTION page and republished from the founder's personal account. Canvas 4:5 (1080×1350), the tallest ratio the feed shows uncropped.
- Original voice, French captions — the audience is French-speaking.
- Word-by-word highlight: the whole caption is on screen, words light up (white) as they are said, the rest stays dimmed.
- Framed source: the excerpt sits in a lemon-edged window on the ink ground with a lemon dot grid, so the viewer sees it is an excerpt.
- No boxes, no on-screen text overlays: a BBH headline above the frame carries the context instead.
Rendering never authorizes publication.
Reading the instruction
| What | Examples | Default |
|---|---|---|
| Source | a file path; a YouTube URL for credit | the file given |
| Passage | « arrête-toi quand il dit… », « tout » | the speaker's whole intervention around the quoted sentence |
| Folder | given path | the operator's social production folder, as Publie/<date>/Extraits-<Speaker>/<slug>/ (ask once if unknown) |
Say in one sentence what will be produced, then run. Ask only when the passage cannot be located or the file cannot be read.
Steps
SKILL below is this skill's folder
(${CLAUDE_PLUGIN_ROOT}/skills/bigemotion-reel-clip). Run npm install there
once if node_modules/ is missing; it fetches playwright-core, which uses the
Chromium Playwright keeps in its user cache (npx playwright-core install chromium if none is there). FFmpeg must be on the PATH.
What ships with it
16 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.
- assets/fonts/bbh-hegarty-v1-latin-regular.ttf 22 KB
- assets/fonts/bricolage-grotesque-v9-latin-500.ttf 47 KB
- assets/fonts/bricolage-grotesque-v9-latin-800.ttf 47 KB
- assets/logo.png 39 KB
- package-lock.json 648 B
- package.json 186 B
- references/descriptions.md 1.7 KB
- references/verification.md 1.2 KB
- scripts/layout.mjs 906 B runs code
- scripts/layout.test.mjs 683 B runs code
- scripts/plan.mjs 7.3 KB runs code
- scripts/plan.test.mjs 5.5 KB runs code
- scripts/render.mjs 11 KB runs code
- scripts/render.test.mjs 5.2 KB runs code
- scripts/transcribe.mjs 4.7 KB runs code
- scripts/transcribe.test.mjs 1.1 KB runs code
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.
- today First seen · 156 lines · 150 tokens per session scan A 1c6ccccefea4
bigemotion-reel-clip is a skill published in the GitHub repository big-emotion/agent-atelier (3 stars, last pushed 2d ago), licensed MIT. It adds 150 tokens to every session and 2,220 once invoked, about $0.0006 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 2026-10-16.
Other skills, from other repositories
github-pr-review
Handles PR review comments and feedback resolution. Use when user wants to resolve PR comments, handle review feedback, fix review comments, address PR review, check review status, respond to reviewer, verify PR readiness, review PR comments, analyze review feedback, evaluate PR comments, assess review suggestions, or…
privacy-guard
Prevents private infrastructure details (node hostnames, internal project names, local usernames and personal emails, absolute home paths, private and VPN IP ranges) from leaking into public repositories through commits, PRs, docs or release artifacts. Use when working in a public or soon-to-be-public repo, before…
github-pr-merge
Merges GitHub Pull Requests after validating pre-merge checklist. Use when user wants to merge PR, close PR, finalize PR, complete merge, approve and merge, or execute merge. Runs pre-merge validation (tests, lint, CI, comments), confirms with user, merges with proper format, handles post-merge cleanup.
github-pr-creation
Creates GitHub Pull Requests with automated validation and task tracking. Use when user wants to create PR, open pull request, submit for review, or check if ready for PR. Analyzes commits, validates task completion, generates Conventional Commits title and description, suggests labels. NOTE - for merging existing…
git-commit
Creates git commits following Conventional Commits format with type/scope/subject. Use when user wants to commit changes, create commit, save work, or stage and commit. Enforces project-specific conventions from CLAUDE.md.
second-opinion
Get second opinions on freshly written code from fresh Codex and Claude reviewers, one small batch at a time, then settle every finding against ground truth before accepting or vetoing it. Use when requested, when project instructions require review before commits, or as part of an active review workflow after tests…