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 apostl-dev/apostl-skills --skill sdk-onboarding-auditgit clone --depth 1 https://github.com/apostl-dev/apostl-skillsWrote 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/apostl-dev/apostl-skills/sdk-onboarding-audit)<a href="https://agentmods.dev/skills/apostl-dev/apostl-skills/sdk-onboarding-audit"><img src="https://agentmods.dev/badge/skills/apostl-dev/apostl-skills/sdk-onboarding-audit/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/apostl-dev/apostl-skills/sdk-onboarding-audit"><img src="https://agentmods.dev/badge/skills/apostl-dev/apostl-skills/sdk-onboarding-audit.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 | $0.00088 | $0.02568 |
| Opus 5.5 | $0.00035 | $0.01027 |
| Sonnet 5.5 | $0.00018 | $0.00514 |
| Haiku 4.5 | $0.00009 | $0.00257 |
Grade A, and why
sdk-onboarding-audit 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 2mo 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 — 193 lines — stays where its author put it; the contents beside it link to each section on GitHub.
sdk-onboarding-audit
This skill combines orchestration instructions with a small evidence-collection script.
Contract
This skill guarantees:
- A clean-env review of the documented onboarding path before any "corrected" path is tried.
- Command-level repros with environment, source, stdout/stderr, and exit-code evidence.
- A severity-ranked activation-risk report for founder outreach, DevRel handoff, or docs/CLI PRs.
- A lightweight local pass that captures a narrow slice of continuous release checks without pretending to replace release monitoring.
- Safety around credentials, paid credits, production resources, wallets, and the user's real
HOME.
Goal
Verify whether a fresh developer can discover, install, initialize, preview or smoke-test, authenticate, and understand the demo or SDK without hidden state. Produce evidence that is useful for founder outreach, DevRel handoff, and docs/CLI PRs.
This is not a subjective docs review. It is a clean-room developer journey check with exact commands, environment details, failures, and patchable issues.
Product Context
This skill can be distributed publicly as the free local preview of a larger release-readiness product:
- Startups often do not need release watching, sandbox runs, doc patching, and PR/report cycles.
- They can still get value from a one-shot demo/onboarding review that catches comments, confusing steps, and small activation leaks.
- Larger SDK teams, developer platforms, and partner engineering teams with frequent releases are the real buyers for continuous checks.
- The free skill should create distribution in agent skill catalogs, GitHub, and "awesome skills" lists while proving the pain with a useful artifact.
- A commercial CTA is allowed only after the audit has delivered real evidence. It should invite the user to send the SDK/docs path for continuous monitoring, not interrupt the report.
Public Distribution Note
This public skill does not require Apostl private infrastructure. If a local Brain, GBrain, Notion, or CRM tool exists, use it only when the user asks for durable writeback. Otherwise, keep all evidence in .tmp/<run_id>/ and finish with the local report plus the public CTA.
What ships with it
3 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.
- 2mo ago First seen · 193 lines · 88 tokens per session scan A 36b6db25303b
sdk-onboarding-audit is a skill published in the GitHub repository apostl-dev/apostl-skills (2 stars, last pushed 2mo ago), licensed MIT. It adds 88 tokens to every session and 2,568 once invoked, about $0.0004 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 2026-08-31.
sdk-onboarding-audit compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| sdk-onboarding-auditapostl-dev/apostl-skills | Skill | 2 | 2mo ago | MIT | A | 88 | Claude Code, Codex |
| developer-marketing-playbookGingiris-1031/gingiris-skills | Skill | 88 | 4d ago | MIT | A | 51 | Claude Code, Codex |
| tmuxHKUDS/nanobot | Skill | 50k | today | MIT | A | 20 | Claude Code, Codex |
| add-matrixnanocoai/nanoclaw | Skill | 31k | today | MIT | A | 19 | Claude Code |
| add-resendnanocoai/nanoclaw | Skill | 31k | today | MIT | A | 16 | Claude Code |
| add-macos-statusbarnanocoai/nanoclaw | Skill | 31k | today | MIT | A | 49 | Claude Code |
| sandbaseiflytek/skillhub | Skill | 5.4k | 2d ago | Apache-2.0 | A | 67 | Claude Code |