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-create-packmind-datasetWrote 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-create-packmind-dataset)<a href="https://agentmods.dev/skills/packmindhub/packmind/michel-create-packmind-dataset"><img src="https://agentmods.dev/badge/skills/packmindhub/packmind/michel-create-packmind-dataset/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-create-packmind-dataset"><img src="https://agentmods.dev/badge/skills/packmindhub/packmind/michel-create-packmind-dataset.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to high
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 →
- high Privilege Escalation · line 106 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- medium Data Exfiltration · line 36 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Rogue Agent · line 51 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00000 | $0.02537 |
| Opus 5.5 | $0.00000 | $0.01015 |
| Sonnet 5.5 | $0.00000 | $0.00507 |
| Haiku 4.5 | $0.00000 | $0.00254 |
Grade A, and why
michel-create-packmind-dataset scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
until curl -sf "localhost:$PM_WEB" >/dev/null; do sleep 2; done # frontend ready How it starts
The opening of the file, as written. The whole thing — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Create a Packmind dataset
Build a working dataset inside a local Packmind instance — an organization with standards, commands, and skills — so a change can be tested against realistic data. Written for an autonomous agent verifying its own work on the Packmind app.
The one rule that governs what you build
Let the task pick the artifacts. This skill is not a fixed recipe that always creates the same three standards. A "dataset" is whatever the thing you are testing needs to be exercised. Before seeding anything, ask: what must exist for my change to be observable?
- Testing a standards-list filter or the Standards page → seed a few standards (samples are fastest).
- Testing the Skills page, skill versioning, or
playbook add/submit→ seed at least one skill via the CLI (the only path that creates skills). - Testing a command palette,
/sluginvocation, or the Commands page → author one or two commands. - Reproducing a bug that only appears with N artifacts, or a specific name/slug → create exactly those.
- Just need "the app isn't empty" for a demo → a few sample standards + one command + one skill is a well-rounded minimum.
Seed the minimum that makes the change observable. Over-seeding slows the run and muddies what you are actually testing. When unsure what an artifact is or how a flow behaves, look it up in the product docs over MCP (see below) rather than guessing.
Product docs are available over MCP
The packmind-user-docs MCP server (configured in .mcp.json, served from https://docs.packmind.com/mcp) exposes Packmind's end-user documentation. Query it whenever you are unsure how a feature works from the user's side — what a standard/command/skill is, what the creation flows offer, what a setting does, how packages/distribution work. This is the authoritative source for product behavior; prefer it to assumptions. The docs describe the UI and concepts; the CLI mechanics below are the seeding path.
Workflow
1. Bring the stack up — defer to michel-run-local-dev-stack
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.
- 1mo ago First seen · 149 lines · 0 tokens per session scan A f6d8dfbae8a0
michel-create-packmind-dataset is a skill published in the GitHub repository PackmindHub/packmind (319 stars, last pushed 2d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 2,537 tokens. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
verifier
Use this skill when verifying that a completed Taniwha implementation or composition satisfies its contract's acceptance criteria. The verifier reads the contract, the implementation's source files, and the project context, then writes its own tests against the contract's acceptance criteria, runs them, and reports…
gsd-verify-work
Validate built features through conversational UAT.
gsd-add-tests
Generate tests for a completed phase based on UAT criteria and implementation.
bad-case-to-dpo
A guide to turning failed production agent runs into training and evaluation data. It explains how to find the first mistake, create preference examples for DPO (Direct Preference Optimization), and check that a fix does not damage other tasks.
character-animation-qa
Review local character animation with schema checks, Playwright browser previews, frame sampling, and FFmpeg/ffprobe final output checks.
tdd
Test-driven development with red-green-refactor loops around vertical slices (tracer bullets), not horizontal layers. Use when asked to "use TDD", "write test-first", "red-green-refactor", "build this with tests", or when a feature has a clear observable contract. The discipline complement to the test/add-tests skills…