Borrowing it
Nothing to install: this file belongs to RoboFinSystems/robosystems. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/RoboFinSystems/robosystems/main/.claude/commands/soc2-review.mdgit clone --depth 1 https://github.com/RoboFinSystems/robosystemsWrote 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/robofinsystems/robosystems/soc2-review)<a href="https://agentmods.dev/commands/robofinsystems/robosystems/soc2-review"><img src="https://agentmods.dev/badge/commands/robofinsystems/robosystems/soc2-review/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/commands/robofinsystems/robosystems/soc2-review"><img src="https://agentmods.dev/badge/commands/robofinsystems/robosystems/soc2-review.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 | $0.00016 | $0.01226 |
| Opus 5.5 | $0.00006 | $0.00490 |
| Sonnet 5.5 | $0.00003 | $0.00245 |
| Haiku 4.5 | $0.00002 | $0.00123 |
Grade A, and why
soc2-review 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 — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Assess SOC 2 readiness: map the security posture to the Trust Services Criteria, inventory policies and evidence, and produce a readiness dashboard plus a before-vs-with-the-auditor remediation plan. This is the compliance-framed companion to /security-audit (which gathers the raw posture).
Pairs with the soc2-readiness-review runbook in local/RoboSystems/runbooks/ — read it alongside this file. This file is the public, generic methodology; the runbook is the live record of the current TSC mapping, which evidence slots are filled, and what the compliance platform already automates. It is authoritative for this environment.
Scope & guardrails
- Read-only by default, same as
/security-audit— describe/list/get andghreads only; neverget-secret-value; every change needs explicit user confirmation. - The readiness report is sensitive — never commit it. The methodology (this skill) is public-safe; the output names your exact unmet controls, disabled services, and audit weaknesses — a roadmap for both attackers and adversarial due-diligence. Write it to a git-ignored path (
local/, scratchpad) or an ephemeral private Artifact. Never commit the readiness report to the repo. - Not attestation or legal advice. This is engineering-readiness guidance. Only a licensed CPA firm can determine SOC 2 compliance and issue a report — say so in the output.
Step 1 — Gather the posture
Run /security-audit (or its Phase 1–6 sweep) for the live control state + findings. Then read the code-level and documentary controls:
SECURITY.md(control catalog) androbosystems/security/modules.- The written policy set and any risk-acceptance register (in the git-ignored design vault
local/RoboSystems/if present — e.g.ref/security.md,policies/). Note which of the auditor-expected policies exist vs are missing (infosec, access control, change management, incident response, BCDR, vendor/supplier risk, risk assessment, data classification/retention, encryption/key management, SDLC, HR/acceptable-use).
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 · 53 lines · 16 tokens per session scan A 00eb2e111349
soc2-review is a command published in the GitHub repository RoboFinSystems/robosystems (29 stars, last pushed today), licensed Apache-2.0. It adds 16 tokens to every session and 1,226 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 2026-08-30.
Other commands, from other repositories
slm-governance
Governed-workspace behavior for SuperLocalMemory. Covers roles (admin/member/viewer) and company mode, who administers a company-mode workspace (a signed-in admin, or slm team on the SLM computer), slm token show in strict mode, what remote web apps can never see or change, retention and lifecycle settings, the audit…
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.
speckit.bug.fix
Apply the remediation from a bug assessment and record what was changed.