Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/heristop/leclapnpx agentmods add skills/heristop/leclap/evidence-skillWrote 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/heristop/leclap/evidence-skill)<a href="https://agentmods.dev/skills/heristop/leclap/evidence-skill"><img src="https://agentmods.dev/badge/skills/heristop/leclap/evidence-skill/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/heristop/leclap/evidence-skill"><img src="https://agentmods.dev/badge/skills/heristop/leclap/evidence-skill.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 | $0.00043 | $0.05468 |
| Opus 5.5 | $0.00017 | $0.02187 |
| Sonnet 5.5 | $0.00009 | $0.01094 |
| Haiku 4.5 | $0.00004 | $0.00547 |
Grade A, and why
evidence-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 3d 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 — 347 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Evidence video: the LeClap house template
When a task calls for the house before/after evidence video, prepare it for the pull or merge request beside any stills. This skill covers that one workflow: the template behind the render, the script that composes it, and the traps between a Playwright capture and a finished clip.
The video is three parts, joined by 0.5 s fades:
- The slate. A LeClap card on the ink canvas: the mark, the ticket decoding in, the headline in the brand gradient (Oswald, word by word), the change in one line, and the BEFORE and AFTER fields. A sheen crosses the card, with a clap, just before the cut into the comparison.
- The comparison. BEFORE and AFTER play at the same time, in two exact 4:3 panes, each trimmed so
the change lands on the same second. With
freeze, both panes hold on that frame, aframestroke in each side's colour rings the changed area and a one-line callout names what each side does. - The closing card. The same card: what to review, the summary again, where to look first, and "Made with LeClap" typed in.
It is an example from the LeClap repo, written to be dropped into .agents/skills/evidence-video/ of
the app under review. The look is LeClap's on purpose: see "The house look" below before changing it.
The published artifact is the final .mp4, played inline in the description. No GIF anywhere, not
even as a preview or fallback: it is not the deterministic artifact, and it makes the real video easy
to miss.
0. Do not hand-roll it. Run the two files in this directory.
python3 .agents/skills/evidence-video/build.py \
--content <work>/content.json \
--work <work> \
--leclap "npx @leclap/cli" # omit to render with the leclap MCP's compose_video instead
build.py and template.json are the house video together; neither is it alone. The template
draws the slate, the closing card, the highlights and the clap. build.py composes the comparison clip
(the two panes, their badges, titles, descriptions and callouts, the baked freeze), fills the
template's fields with your copy, and checks every string against its box. An agent that copies
template.json and hand-composes its own comparison ships something that looks plausible alone and is
obviously not the house video beside a real one. If you did not run build.py, you did not build the
house video.
What ships with it
4 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.
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.
- 3d ago Changed · -129 lines · +3 tokens per session 94ea9dd8c61c
- 11d ago Changed · +4 lines · -77 tokens per session 177e2798048d
- 17d ago First seen · 472 lines · 117 tokens per session scan A 6ee26c69acee
evidence-video is a skill published in the GitHub repository heristop/leclap (34 stars, last pushed yesterday), licensed MIT. It adds 43 tokens to every session and 5,468 once invoked, about $0.0002 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 2026-09-29.
Other skills, from other repositories
qiaomu-cut
A workflow for turning a brief video idea into a planned, sourced, edited, rendered, and checked video project.
writing-react-native-storybook-stories
Create and edit React Native Storybook stories using Component Story Format (CSF). Use when writing .stories.tsx files, adding stories to React Native components, configuring Storybook addons (controls, actions, backgrounds, notes), setting up argTypes, decorators, parameters, or working with portable stories for…
setup-react-native-storybook
Set up Storybook for React Native in Expo, React Native CLI, or Re.Pack projects. Use when adding Storybook to a project, configuring metro.config.js with withStorybook, creating .rnstorybook configuration files, setting up Storybook routes in Expo Router, configuring getStorybookUI, or adding the StorybookPlugin to a…
uniwind
Uniwind — Tailwind CSS v4 styling for React Native. Use when adding, building, or debugging components in a React Native project that uses Uniwind classNames. Covers setup, Metro config, global.css, theming, className props, accent- color props, platform/data/state/responsive variants, CSS variables, custom utilities…
upgrading-react-native-storybook
Incrementally upgrade React Native Storybook across the supported migration paths. Use when upgrading @storybook/react-native projects from 5.3.x to 6.5.x, 6.5.x to 7.6.x, 7.6.x to 8.3.x, 8.x to 9.x, or 9.x to 10.x. Detect the currently installed Storybook version, choose only the next migration step, update…
expo
Use when shipping a React Native app with Expo — EAS Build/Submit/Update, eas.json profiles and channels, config plugins, prebuild/CNG, runtime-version policy, OTA updates that never land, SDK upgrades, the New Architecture. NOT RN UI, navigation or native-module authoring (that is react-native), NOT a Dart app (that…