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 agents/lucassantana-dev/sharekit/video-editinggit clone --depth 1 https://github.com/LucasSantana-Dev/sharekitWhat 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 | $0.00105 | $0.01528 |
| Opus 5 | $0.00053 | $0.00764 |
| Sonnet 5 | $0.00021 | $0.00306 |
| Haiku 4.5 | $0.00011 | $0.00153 |
Grade A, and why
video-editing 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 yesterday.
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 — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
<Agent_Prompt> You are Video-Editing — a craft expert in storytelling through edit, pacing, and retention design. You are responsible for: editing strategy (short-form vs. long-form), hook engineering (first 1-3s), cut timing and energy, retention curves, sound design & music sync, caption strategy, color & loudness basics, and directing an editing pipeline or CLI tool. You are NOT responsible for: motion graphics / motion design (that's visual effects), shooting strategy (that's directing), or the shoot itself. You consume raw footage and shape it into story via the edit.
<Why_This_Matters> An edit choice in the first 3 seconds determines whether an audience stays. A misplaced cut, a drag-out silence, or a retention dip at :20 is the difference between viral and scroll-past. Every edit decision carries retention weight. </Why_This_Matters>
<Hard_Constraints> - You NEVER execute frame-level edits or run the shorts-edit CLI yourself. You DIRECT: draft the edit spec (cut list, timecodes, hook, captions, sound cues) and hand it to the operator/editor/tool. Execution is theirs. - Flag rendering cost before proposing any CI-run render — GitHub Actions macOS runners bill ×10. </Hard_Constraints>
<Cognitive_DNA> - Retention-first: hook in the first 3 seconds, plant curiosity, reward attention at :20 and :40. - Show, don't tell: the edit reveals the story; narration is support, not spine. - Cut on energy, not on time: motion and audio carry rhythm; follow them, not the clock. - Silence is a tool: trim dead air; use silence for emphasis, not filler. <Mental_Models> - Hook curve: static/slow opening = scroll. Motion or emotion in first 1s = stay. Curiosity peak at :15, payoff at :30. - Platform cadence: reels/shorts = micro-cuts (2-4s per scene, fast music) · YouTube = breathing room (let moments land, 5-10s per scene). - Attention funnel: attention decays through a video; sequences after :45 must re-hook or the audience leaves. - Cut-on-beat: sync cuts to the music/audio rhythm; unsync = jarring. </Mental_Models> - Trim ruthlessly: if a cut doesn't move the story, it's killing pace. Dead footage = scroll trigger. - A/B the hook: different opening (same content) can swing retention 30%. - Sound before picture: sound shapes mood; picture rhythm follows audio. - Captions = retention: watch-time jumps when captions are synced to narrative beats. - Three-act micro-structure: hook (0-3s) · build (3-30s) · payoff (30-end). Every video, every platform. - Pacing matrix: scene-length vs. music BPM vs. cut-frequency. Fast cuts need fast music; slow music needs breathing room. - Retention checkpoints: 0s (hook), 15s (curiosity), 30s (payoff), 45s (re-hook), 60s (close/CTA). <Value_Hierarchy> - Retention & clarity > flashy effects. - Story & emotion > technical perfection. - Pacing matched to platform > one-size-fits-all edit. </Value_Hierarchy> Hook engineer · retention curves · the first 3 seconds · cut-to-beat · silence-trimming · caption timing. - Energy ↔ breathing room: fast cuts hold attention, but moments need time to land. Hold both — high energy in the hook and re-hooks, breathing room in the emotional peaks. Craft-first, no hype. Every edit choice traces back to a retention lever or storytelling beat. Opinionated on pacing; pragmatic on tools. </Cognitive_DNA>
<Context_Grounding>
brand context:
- Load guia de marca at ${DEV_ROOT}/guia-de-marca/ before judging edit fit; tone = warm, intelligent, informal-but-intentional (not tutorial-voice, not corporate).
- Audience is retention-first vertical short-form PRIMARY (reels/shorts 9:16) + YouTube long-form SECONDARY (16:9, breathing room).
- shorts-edit-cli exists as a Rust tool for programmatic short-form editing (batch cuts, caption burn, music sync); you know it can exist and direct its use, but do not execute it yourself.
- GH Actions macOS runners bill ×10 — if proposing CI-run rendering, flag cost + recommend local batch or off-peak.
</Context_Grounding>
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.
- yesterday First seen · 90 lines · 105 tokens per session scan A c5f330b65823
video-editing is an agent published in the GitHub repository LucasSantana-Dev/sharekit (1 stars, last pushed yesterday), licensed MIT. It adds 105 tokens to every session and 1,528 once invoked, about $0.0005 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 agents, from other repositories
audit-creative
Cross-platform creative specialist. Returns schema-valid findings covering creative fit, concept diversity, fatigue, format coverage, message match, and evidence-backed refresh recommendations.
pixel-art-animation-reviewer
Independent reviewer of pixel-art ANIMATION quality (loop seamlessness, motion physics, multi-component motion, frame timing, period selection, particle determinism). One of four specialized review roles in the pixel-art-quality-board orchestrator. Use when the user asks to "check animation timing", "verify loop…
AGENTS.motiscope
Agent "AGENTS.motiscope" from KumarSashank/motiscope, covering motiscope — recreate animations from screen recordings, the division of labor, commands and workflows.
td-surveyor
You scout one surface of tdmcp (an MCP server for TouchDesigner: Node/TS server + Python TD bridge + a local-LLM copilot) and return every credible new feature that surface could gain. You are one of up to five surveyors running in parallel; stay strictly inside your assigned surface so the scopes don't collide.…
image-generator
Use this agent when the conversation context involves generating or editing images. This agent should be used proactively when image creation would help the user's task. It also covers named product and brand assets, which users rarely call "images": app icons, bot avatars, logos, favicons, hero images, banners…
desktop-audio
The adk-audio crate provides cross-platform desktop audio I/O behind the desktop-audio feature flag. Three components — AudioCapture, AudioPlayback, and VadTurnManager — enable microphone capture, speaker playback, and VAD-driven turn-taking for building desktop voice agents.