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 commands/samibs/skillfoundry/onboardgit clone --depth 1 https://github.com/samibs/skillfoundryWrote 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/commands/samibs/skillfoundry/onboard)<a href="https://agentmods.dev/commands/samibs/skillfoundry/onboard"><img src="https://agentmods.dev/badge/commands/samibs/skillfoundry/onboard.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.02135 |
| Opus 5 | $0.00000 | $0.01068 |
| Sonnet 5 | $0.00000 | $0.00427 |
| Haiku 4.5 | $0.00000 | $0.00214 |
Grade A, and why
onboard 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 — 300 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/onboard — SkillFoundry First-Run Setup
Role: Interactive setup wizard that detects the project stack, verifies shell execution, configures the framework, and walks the user through their first workflow.
Usage
/onboard First-run or re-run setup
/onboard --reset Clear all detected state and start fresh
/onboard --quiet Run detection only, no prompts
When to use
- First time SkillFoundry is used in a project
- After switching to a different project type (e.g., added Playwright)
- When
/testloopor/featurereports wrong commands - When stack changed (new test framework, new package manager)
Behavior
Execute these steps in order:
Step 1: Welcome
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
SKILLFOUNDRY ONBOARDING
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
This wizard will:
1. Detect your project stack and test commands
2. Verify shell execution is available
3. Configure framework settings
4. Run a minimal test to confirm everything works
5. Show you the two commands you need to start
Takes about 5 minutes. You can run /onboard again any time.
Step 2: Git check
git rev-parse --git-dir >/dev/null 2>&1 || echo "NO_GIT"
If no git repo:
⚠️ No git repository found.
SkillFoundry requires git for commit tracking and state management.
Initialize now? (recommended)
→ git init && git add -A && git commit -m "initial commit"
Auto-initialize if user confirms. If user declines, warn that /feature commit stage will not work.
Step 3: Execution context detection
Run agents/_execution-context.md detection algorithm.
Display result clearly:
EXECUTION CONTEXT
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
Shell access: ✓ Available
Project root: ✓ /path/to/project
Mode: REAL (commands execute and results are verified)
Or if advisory:
Shell access: ✗ Not available
Mode: ADVISORY (static analysis only — manual verification required)
To enable real execution: use Claude Code CLI (not the web UI)
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 · 300 lines · 0 tokens per session scan A 8f10d07c3795
onboard is a command published in the GitHub repository samibs/skillfoundry (12 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,135 tokens. 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 commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.