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.
git clone --depth 1 https://github.com/nathanimphilipos/synergos-grcWrote 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/nathanimphilipos/synergos-grc/control-lookup)<a href="https://agentmods.dev/commands/nathanimphilipos/synergos-grc/control-lookup"><img src="https://agentmods.dev/badge/commands/nathanimphilipos/synergos-grc/control-lookup/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/nathanimphilipos/synergos-grc/control-lookup"><img src="https://agentmods.dev/badge/commands/nathanimphilipos/synergos-grc/control-lookup.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 | $0.00009 | $0.01985 |
| Opus 5 | $0.00005 | $0.00992 |
| Sonnet 5 | $0.00002 | $0.00397 |
| Haiku 4.5 | $0.00001 | $0.00198 |
Grade A, and why
control-lookup 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 10d 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.
This is a copy
86% identical to control-lookup — 8 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/grc:control-lookup
Look up controls by framework and ID or keyword.
Usage
/grc:control-lookup [framework] [id-or-keyword]
Arguments
- framework: The compliance framework to search. Accepts:
nist,fedramp,fisma,cmmc,soc2,iso27001,pci,hipaa,cis,cobit,ccm,gdpr - id-or-keyword: A control ID (e.g.,
ac-2,CC6.1,A.8.1) or a keyword (e.g.,multi-factor,encryption,logging)
Examples
/grc:control-lookup nist ac-2
/grc:control-lookup soc2 CC6.1
/grc:control-lookup pci 8.3
/grc:control-lookup nist encryption
/grc:control-lookup iso27001 A.8.5
/grc:control-lookup cis 5.2
Behavior
When invoked:
-
Identify the framework from the first argument. Normalize aliases:
nist/800-53→ NIST 800-53 Rev 5fedramp→ FedRAMP (NIST 800-53 + FedRAMP parameters)cmmc/800-171→ CMMC 2.0 / NIST 800-171soc2/soc→ SOC 2 Trust Services Criteriaiso/iso27001/27001→ ISO 27001:2022pci/pcidss→ PCI DSS v4.0.1hipaa→ HIPAA Security Rulecis→ CIS Controls v8.1cobit→ COBIT 2019ccm/csa→ CSA CCM v4gdpr→ GDPR
-
For NIST or FedRAMP lookups, read the OSCAL family JSON first for authoritative control data:
- Determine the family ID from the control ID (e.g.,
AC-2→ familyac,IA-5(1)→ familyia) - For
nist: readskills/grc-knowledge/oscal/nist-800-53-rev5/{family}.json - For
fedramp: readskills/grc-knowledge/oscal/fedramp-moderate-rev5/{family}.json - IMPORTANT: Use the Read tool to read the file directly. Do NOT use Bash, Python, jq, or any other scripting tool to extract data from OSCAL files. The JSON is structured and you can find the target control by scanning for its
"id"field. For large family files, you may read the file in chunks using offset/limit parameters to locate the control. - ID normalization: OSCAL uses lowercase with dots for enhancements —
AC-2→ac-2,AC-2(1)→ac-2.1 - Extract from OSCAL (jq paths shown for reference — extract visually from the JSON, do not run jq):
- Control statement:
.controls[] | select(.id == "ac-2") | .parts[] | select(.name == "statement") - Parameters:
.controls[].params[]— look forid,label,guidelines,select/choiceconstraints. FedRAMP files include.constraints[].descriptionwith required values (e.g., "at least every 3 years") - Guidance:
.parts[] | select(.name == "guidance") - Assessment objectives:
.parts[] | select(.name == "assessment-objective")— nested tree of testable objectives with.prosefor each leaf - Assessment methods:
.parts[] | select(.name == "assessment-method")— three methods per control:- EXAMINE (
.props[] | select(.name == "method") | .value == "EXAMINE"): lists documents/artifacts an assessor reviews - INTERVIEW: lists roles an assessor interviews
- TEST: lists processes/mechanisms an assessor tests
- Each method's objects are in
.parts[] | select(.name == "assessment-objects") | .prose
- EXAMINE (
- Enhancements:
.controls[].controls[](nested under parent) - Related controls:
.links[] | select(.rel == "related")
- Control statement:
- Then read the markdown framework file from
skills/grc-knowledge/frameworks/for cross-framework mapping, audit context, and narrative guidance
- Determine the family ID from the control ID (e.g.,
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.
- 10d ago First seen · 152 lines · 9 tokens per session scan A 7971cdeeb7ac
control-lookup is a command published in the GitHub repository nathanimphilipos/synergos-grc (5 stars, last pushed 6mo ago), licensed MIT. It adds 9 tokens to every session and 1,985 once invoked, about $0.0000 per session on Opus 5. A static security scan graded it A with 0 findings. It is 86% identical to control-lookup, differing in 8 lines, and is treated as a copy.
Other commands, from other repositories
deps-audit
Audit project dependencies for vulnerabilities, outdated packages, license conflicts, and supply chain risks — then provide actionable remediation strategies.
review-epo-claims
Analyze patent claims for EPO Art. 84 EPC compliance - clarity, conciseness, support by description.
voice-compliance
Voice/telephony compliance check — invokes voice-ai-reviewer to produce TM-voice-{slug}.md with TCPA, STIR/SHAKEN, state recording-consent, EU AI Act Art. 50, and synth-voice deepfake-law gaps.
review-policy
Review a policy document for structure, coverage, and language quality.
at-dsgvo
You are helping an enterprise architect generate an Austrian Data Protection Assessment — the Austrian-specific GDPR layer applied by the Datenschutzbehörde (DSB) under the Datenschutzgesetz (DSG 2018, BGBl. I Nr. 165/1999 as amended). Run this after /arckit:eu-rgpd to add Austrian obligations that go beyond the EU…
au-pspf
You are an enterprise architect generating a Protective Security Policy Framework (PSPF) compliance assessment for an Australian Government entity or contractor handling government information.