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 skills add Mathews-Tom/armory --skill concept-to-videogit clone --depth 1 https://github.com/Mathews-Tom/armoryWrote 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/mathews-tom/armory/concept-to-video)<a href="https://agentmods.dev/skills/mathews-tom/armory/concept-to-video"><img src="https://agentmods.dev/badge/skills/mathews-tom/armory/concept-to-video/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/mathews-tom/armory/concept-to-video"><img src="https://agentmods.dev/badge/skills/mathews-tom/armory/concept-to-video.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00070 | $0.04336 |
| Opus 5 | $0.00035 | $0.02168 |
| Sonnet 5 | $0.00014 | $0.00867 |
| Haiku 4.5 | $0.00007 | $0.00434 |
Grade A, and why
concept-to-video 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 10d 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 — 342 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Concept to Video
Creates animated explainer videos from concepts using Manim (Python) as a programmatic animation engine.
Reference Files
| File | Purpose |
|---|---|
references/rules/pipeline-flow.md |
RAG, ETL, CI/CD — sequential stage animations with arrows |
references/rules/architecture-layers.md |
System stacks, network layers, abstraction hierarchies |
references/rules/algorithm-stepthrough.md |
Sorting, search, graph traversal — stateful step-by-step animations |
references/rules/comparison.md |
Side-by-side A vs B, before/after, trade-off visualizations |
references/rules/agent-interaction.md |
Multi-agent message passing, distributed systems, pub/sub |
references/rules/math-concept.md |
Equations, formulas, geometric proofs — LaTeX-free by default |
references/rules/training-loop.md |
Gradient descent, RL loops, cyclic iterative processes |
references/rules/transitions.md |
Fade and wipe transitions between scene sections |
references/rules/text-animation.md |
Text replacement, progressive bullet reveal, callouts, emphasis |
references/rules/layout.md |
Canvas coordinates, VGroup arrangement, spacing guidelines |
references/rules/audio-overlay.md |
ffmpeg audio overlay — background music, voiceover, multi-track mixing |
references/rules/voiceover-scaffold.md |
Timing script generation, TTS handoff, narration best practices |
references/rules/images.md |
ImageMobject usage, logo/screenshot patterns, scaling and positioning |
references/rules/subtitles.md |
SRT generation from scene timing, ffmpeg subtitle burning |
references/rules/multi-scene.md |
Multiple Scene classes, ffmpeg concat, chapter-based composition |
references/templates/data_flow_template.py |
Parametric pipeline/data flow animation (config-driven STAGES list) |
references/templates/comparison_template.py |
Parametric side-by-side comparison (config-driven LEFT/RIGHT items) |
references/templates/timeline_template.py |
Parametric timeline animation (config-driven EVENTS list) |
scripts/render_video.py |
Wrapper around Manim CLI — handles quality, format, output path cleanup |
scripts/add_audio.py |
ffmpeg wrapper — audio overlay, volume, fade-in/out, trim-to-video |
What ships with it
38 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.
- config.toml 479 B
- evals/cases.yaml 6.2 KB
- pyrightconfig.json 161 B
- references/code2video/coder.md 5.9 KB
- references/code2video/critic.md 5.8 KB
- references/code2video/LICENSE 1.0 KB
- references/code2video/planner.md 4.3 KB
- references/rules/agent-interaction.md 3.3 KB
- references/rules/algorithm-stepthrough.md 3.4 KB
- references/rules/architecture-layers.md 2.4 KB
- references/rules/audio-overlay.md 2.5 KB
- references/rules/comparison.md 3.0 KB
- references/rules/images.md 2.9 KB
- references/rules/layout.md 3.3 KB
- references/rules/math-concept.md 2.9 KB
- references/rules/multi-scene.md 3.1 KB
- references/rules/pipeline-flow.md 2.2 KB
- references/rules/subtitles.md 3.0 KB
- references/rules/text-animation.md 3.0 KB
- references/rules/training-loop.md 3.1 KB
- references/rules/transitions.md 2.5 KB
- references/rules/voiceover-scaffold.md 2.8 KB
- references/storyboard-schema.md 3.4 KB
- references/templates/comparison_template.py 3.5 KB runs code
- references/templates/data_flow_template.py 2.8 KB runs code
- references/templates/timeline_template.py 3.3 KB runs code
- scripts/_config.py 1.1 KB runs code
- scripts/_fixup_client.py 4.0 KB runs code
- scripts/add_audio.py 4.6 KB runs code
- scripts/critic_pass.py 13 KB runs code
- scripts/fetch_assets.py 11 KB runs code
- scripts/plan_storyboard.py 7.0 KB runs code
- scripts/render_video.py 11 KB runs code
- tests/conftest.py 219 B runs code
- tests/test_critic_pass.py 19 KB runs code
- tests/test_fetch_assets.py 16 KB runs code
- tests/test_plan_storyboard.py 9.7 KB runs code
- tests/test_render_video_autofix.py 15 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.
- 10d ago First seen · 342 lines · 70 tokens per session scan A fdec04b4ad09
concept-to-video is a skill published in the GitHub repository Mathews-Tom/armory (316 stars, last pushed 4d ago), licensed MIT. It adds 70 tokens to every session and 4,336 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 2026-08-30.
Other skills, from other repositories
art-director
Orchestrate iterative visual style searches with branch prompts, decision graphs, feedback loops, and final direction selection.
magazine-web-ppt
For marketing and gtm work: bind launches, campaigns, events, and brand plans to growth and pipeline outcomes. Built around the core query "annual-marketing-plan", with GTM strategy lead judgment, buyer-ready proof, and this outcome: approve launch plan, campaign budget, or GTM motion.
html-ppt-zhangzara-coral
OpenDesign's community-growth campaign across GitHub, Discord, and X: the loops, the content calendar, and the pipeline math. Built as a decision-grade marketing & GTM deck for growth team, community lead.
html-ppt-zhangzara-daisy-days
A customer-success workshop onboarding users to a project-management app — the first-value path and the habits that retain. Built as a decision-grade professional training deck for new customers, CS team.
html-ppt-zhangzara-long-table
OpenDesign's unit-economics and BYOK cost model: the assumptions, the sensitivity, and why it scales. Built as a decision-grade data & finance deck for CFO, investors.
html-ppt-zhangzara-mat
A margin-recovery diagnosis for a regional grocery chain — the governing thought, the driver tree, the priorities, and the roadmap. Built as a decision-grade consulting deck for client sponsor, steering committee.