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 smicolon/ai-kit --skill onboard-context-providergit clone --depth 1 https://github.com/smicolon/ai-kitWrote 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/smicolon/ai-kit/onboard-context-provider)<a href="https://agentmods.dev/skills/smicolon/ai-kit/onboard-context-provider"><img src="https://agentmods.dev/badge/skills/smicolon/ai-kit/onboard-context-provider/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/smicolon/ai-kit/onboard-context-provider"><img src="https://agentmods.dev/badge/skills/smicolon/ai-kit/onboard-context-provider.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 | $0.00063 | $0.00753 |
| Opus 5.5 | $0.00025 | $0.00301 |
| Sonnet 5.5 | $0.00013 | $0.00151 |
| Haiku 4.5 | $0.00006 | $0.00075 |
Grade A, and why
onboard-context-provider 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 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.
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 — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Onboard Context Provider
Provides personalized explanations and assistance based on the engineer's background from their onboarding profile.
Activation Triggers
This skill activates when:
- Engineer asks "how do I..." or "where do I put..." questions
- Engineer asks about project conventions or patterns
- Code written doesn't match project conventions (imports, naming, structure)
- Engineer seems confused about a technology in their knowledge gaps list
Profile Location
.claude/onboard-profile.local.md
If this file doesn't exist, this skill does nothing. The engineer needs to run /onboard first.
Behavior
1. Read Engineer Profile
Check .claude/onboard-profile.local.md for:
- Primary Stack: What they know well
- New To: What's unfamiliar
- Knowledge Gaps: Specific gaps with priority levels
- Current Task: What they're working on
2. Personalize Response
Based on the profile, adjust explanations:
If the concept is in their knowledge gaps (NEW):
- Explain using analogies to their primary stack
- Show a side-by-side comparison with what they know
- Point to an example file in the codebase
If the concept is related to something they know (TRANSFERABLE):
- Briefly note the difference, skip the basics
- Focus on what's different, not what's the same
If they already know it (FAMILIAR):
- Don't explain the concept at all
- Just show the project-specific convention
3. Always Include
- Specific file paths from this project as examples
- The project convention (from CLAUDE.md) for whatever they're doing
- A concrete next action they can take
Personalization Strategies
Backend Engineer → Frontend Project
| Concept | Explain As |
|---|---|
| Components | "Like views that return HTML directly" |
| State (useState) | "Like a variable that re-renders the page when changed" |
| Props | "Like function arguments for components" |
| useEffect | "Like Django signals — side effects triggered by changes" |
| Client vs Server Components | "Server = Django view, Client = JavaScript in template" |
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 · 99 lines · 63 tokens per session scan A ee67852c894c
onboard-context-provider is a skill published in the GitHub repository smicolon/ai-kit (6 stars, last pushed 1mo ago), licensed MIT. It adds 63 tokens to every session and 753 once invoked, about $0.0003 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 2026-09-03.
Other skills, from other repositories
apply-grow-coaching
Use when a manager wants to help a direct report solve a problem, develop a skill, or reach a goal through structured questioning rather than advice-giving — because telling people answers builds dependency while coaching builds self-sufficiency.
apply-intrinsic-motivation
Use when a manager wants to design work, roles, or conditions that sustain employee motivation over the long term — by understanding what drives internal engagement rather than relying primarily on compensation, perks, or external incentives.
coaching-techniques
GROW model, active listening, developmental feedback, and team growth approaches.
apply-five-commander-virtues
Use when assessing, developing, or hiring for leadership capability — to evaluate a leader against the five virtues that Sun Tzu identifies as determinants of strategic success and diagnose which virtue deficits are causing organisational or competitive failures.
continuing-education-coordinator
Expert-level Continuing Education Coordinator with deep knowledge of adult learning theory (Andragogy), professional development standards, workforce training regulations, and CE accreditation requirements.
academic-director
Expert Academic Director with 20+ years experience in K-12 or higher education administration, curriculum planning, teacher supervision, and academic standards. Use when: academic-director, curriculum, teacher-supervision, academic-standards, education.