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/PackmindHub/packmindnpx agentmods add skills/packmindhub/packmind/michel-cli-demo-recorderWrote 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/packmindhub/packmind/michel-cli-demo-recorder)<a href="https://agentmods.dev/skills/packmindhub/packmind/michel-cli-demo-recorder"><img src="https://agentmods.dev/badge/skills/packmindhub/packmind/michel-cli-demo-recorder/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/packmindhub/packmind/michel-cli-demo-recorder"><img src="https://agentmods.dev/badge/skills/packmindhub/packmind/michel-cli-demo-recorder.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 10 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Memory Poisoning · line 43 Skill attempts to fill the context window with filler content, displacing legitimate instructions and safety constraints. This can degrade agent performance or bypass safety boundaries.Fix: Implement context-window management that detects and rejects padding or stuffing attempts. Prioritize system instructions over user-injected content.
- medium Prompt Injection · line 43 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 45 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 46 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 47 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 48 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 50 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 51 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 52 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 53 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
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 | $0.00212 | $0.02967 |
| Opus 5 | $0.00106 | $0.01484 |
| Sonnet 5 | $0.00042 | $0.00593 |
| Haiku 4.5 | $0.00021 | $0.00297 |
Grade A, and why
michel-cli-demo-recorder 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 5d 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 — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLI Demo Recorder
Turn a local packmind-cli invocation into a polished, colored terminal screenshot that drops straight into a GitHub PR. The renderer writes a crisp master SVG and, by default, rasterizes it to a PNG next to it — the PNG is the artifact you embed, because GitHub refuses to render SVG in a PR/issue body (its image proxy rejects image/svg+xml). The companion to michel-ui-demo-recorder — that one records the browser UI; this one captures the terminal.
When to reach for this skill
- You just implemented or changed a CLI command/flag/output and are opening or updating a PR.
- "Add a screenshot of the CLI to the PR", "show what the command prints", "prove it runs".
- A bug was about terminal rendering (colors, alignment, truncation) and the fix needs visual evidence.
- Anytime the PR diff includes CLI source (
apps/cli/) — attach a demo by default; reviewers shouldn't have to clone and run it to see the output.
The deliverable is one or more terminal-window images, each showing a fake prompt line (user@host dir % <command>) followed by the command's real, fully-colored output. The renderer emits two files per demo: a .svg master (crisp at any zoom, a few KB, exact-color — keep it as the source) and a .png rasterized from it. Embed the PNG in the PR — GitHub does not render SVG in PR/issue bodies, so an embedded SVG shows up broken. The PNG is what reviewers actually see.
Why a skill exists for this
Capturing colored CLI output correctly has several non-obvious traps that waste time if you hit them mid-task:
- Color dies when stdout isn't a TTY.
packmind-clicolors its output withchalk(seeapps/cli/src/infra/utils/consoleLogger.ts), which — like most well-behaved CLIs — emits ANSI only when it detects a real terminal orFORCE_COLORis set. Pipe the output to a file with neither and you get plain, colorless text — the exact opposite of the goal. The bundled converter both setsFORCE_COLOR=3and runs the command under a pseudo-terminal (PTY), so color survives even for commands that gate strictly onisTTY. Don't hand-roll the capture. - The PTY tool differs by OS. macOS ships BSD
script(script -q <file> <cmd>); Linux ships util-linuxscript(script -qec "<cmd>" <file>). And BSDscriptonly writes the full session to its typescript file, not to a piped stdout. The bundled converter handles both — don't hand-roll it. - GitHub does not render SVG in PR/issue bodies — at all. Its image proxy (Camo) refuses
image/svg+xml, so anembed shows up broken no matter whether you use a relative path, a/raw/URL, orraw.githubusercontent.com. (A committed.svgdoes render on the github.com file view, but that's not where a PR demo lives.) PNG has no such restriction. So: rasterize the SVG to PNG and embed the PNG. The renderer does this automatically. - No SVG rasterizer = no PNG. The PNG step shells out to
rsvg-convert(packagelibrsvg2-bin), which is baked into the Michel worker image (fly/Dockerfile.worker). On a dev Mac without it, the script falls back toqlmanage(ships with macOS); installbrew install librsvgfor the primary path. If neither exists the script errors with the install hint — don't paper over it with--no-pngand then embed a broken SVG.
What ships with it
1 file 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.
- 5d ago First seen · 116 lines · 212 tokens per session scan A 541f9d619abe
michel-cli-demo-recorder is a skill published in the GitHub repository PackmindHub/packmind (310 stars, last pushed today), licensed Apache-2.0. It adds 212 tokens to every session and 2,967 once invoked, about $0.0011 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 2026-09-03.
Other skills, from other repositories
gsd-reapply-patches
Reapply local modifications after a GSD update.
skill-design-lineage
Persist design documents with branch tracking, revision chains, and cross-session discovery.
gsd-undo
Safe git revert. Roll back phase or plan commits using the phase manifest with dependency checks.
seedance-2-5
Generate 4-30 second cinematic video with ByteDance Seedance 2.5 through fal.ai, Volcengine Ark, Runway, or ComfyUI Partner Nodes. Use for long single generations, synchronized audio, and large multimodal reference sets (up to 30 images, 10 videos, and 10 audio clips). Also covers the 2.5 prompt contract: section…
comfyui
Use when working with ComfyUI workflows in OpenMontage, including comfyuiimage/comfyuivideo/comfyuimusic, custom workflowjson/workflowpath inputs, outputnode selection, missing model setup, LoRAs, low-VRAM workflow choices, and community workflow imports.
ltx2
AI video generation with LTX-2.3 22B — text-to-video, image-to-video clips for video production. Use when generating video clips, animating images, creating b-roll, animated backgrounds, or motion content. Triggers include video generation, animate image, b-roll, motion, video clip, text-to-video, image-to-video.