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 nitinjain999/platform-skills --skill compliancegit clone --depth 1 https://github.com/nitinjain999/platform-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/nitinjain999/platform-skills/compliance)<a href="https://agentmods.dev/skills/nitinjain999/platform-skills/compliance"><img src="https://agentmods.dev/badge/skills/nitinjain999/platform-skills/compliance/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/nitinjain999/platform-skills/compliance"><img src="https://agentmods.dev/badge/skills/nitinjain999/platform-skills/compliance.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 | $0.00031 | $0.01556 |
| Opus 5.5 | $0.00012 | $0.00622 |
| Sonnet 5.5 | $0.00006 | $0.00311 |
| Haiku 4.5 | $0.00003 | $0.00156 |
Grade A, and why
compliance 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 today.
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 — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are acting as a senior platform engineer with deep knowledge of SOC 2 compliance for infrastructure-as-code. The user has invoked /platform-skills:compliance with the following input:
$ARGUMENTS
Read references/compliance.md before responding.
Interactive Wizard (fires when no arguments are provided)
When invoked with no arguments, ask before proceeding:
Q1 — Topic?
What do you need?
1. gap — SOC 2 gap analysis of Terraform configuration
2. control — implement a specific SOC 2 control
3. evidence — collect audit evidence for an auditor
4. remediate — fix a specific compliance finding (Checkov rule ID or description)
5. checklist — full SOC 2 readiness checklist
Enter 1–5 or topic name:
Scanning mechanics: To run Checkov scans — static, plan-level, multi-cloud, with fix mode — use
/platform-skills:checkov. This command handles SOC 2 control mapping and evidence collection.Kubernetes side: Kubescape's
SOC2framework checks seven cluster controls and names the criteria in each title — C-0260 Firewall (CC6.1, CC6.6, CC7.2), C-0012 misplaced secrets (CC6.1, CC6.6, CC6.7), C-0186 access to secrets (CC6.1, CC6.6, CC6.7), C-0035 admin access (CC6.1, CC6.2, CC6.7, CC6.8), C-0067 event logging (CC6.8, CC7.1, CC7.2), C-0263 Ingress TLS (CC6.1, CC6.6, CC6.7), C-0264 encrypted PersistentVolumes (CC1.1, CC6.7). Run it with/platform-skills:kubescape clusterand map the results here.
Q2 — Context (after topic selected, one at a time):
- gap:
Paste your Terraform resource(s) or describe the configuration to assess: - control:
Which SOC 2 criterion? (e.g. CC6.7, CC7.2, A1.2) or describe the control to implement: - evidence:
Which criterion or area needs evidence? (e.g. CC7.2 CloudTrail, CC6.7 encryption): - remediate:
Paste the finding or Checkov rule ID (e.g. CKV_AWS_19) and the failing resource: - checklist: no follow-up needed — proceed directly
Then proceed into the relevant section below.
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.
- today Changed · +3 lines e3b358af57c5
- 6d ago First seen · 129 lines · 31 tokens per session scan A 67f7c7408bfd
compliance is a skill published in the GitHub repository nitinjain999/platform-skills (70 stars, last pushed today), licensed Apache-2.0. It adds 31 tokens to every session and 1,556 once invoked, about $0.0001 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 2026-10-12.
Other skills, from other repositories
advisor-ethicist
Use when weighing ethical implications, assessing stakeholder impact, evaluating responsible AI practices, or considering long-term consequences. Analyze decisions through an ethical lens — evaluate who benefits and who bears risk, assess reputation trajectory, and apply moral frameworks.
plagiarism-checker
Scans lyrics for phrases that may match existing songs using web search and LLM knowledge. Use before release to check for unintentional borrowing.
agreement
Maintain sourced agreement context and scope in PROJECT.md, cite registered contracts/proposals, and record amendments without imposing a commercial workflow.
alive:demo
Generate a believable, lived-in ALIVE world from a free-text persona description (custom path) or a deterministic sandbox preset. Routes the create/list/activate/deactivate/delete/status surface and orchestrates the 5-stage subagent generation pipeline.
levy
Domain knowledge agent for Japanese income tax filing (kakutei shinkoku). Guides income classification, deduction optimization, tax calculation, and filing for freelancers, sole proprietors, and side-business earners. Does not write code.
alive:session-history
Revive sessions (quick or heavy), browse, and search — 'what happened recently?', 'find the session where we discussed X', 'revive yesterday's session'. For single-session recall and multi-session browsing. If the human needs to merge multiple sessions into one working context or detect conflicts between parallel…