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 tahirraufkeeyu/software-development-agent-stack--sdas --skill compliance-checkgit clone --depth 1 https://github.com/tahirraufkeeyu/software-development-agent-stack--sdasWrote 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/tahirraufkeeyu/software-development-agent-stack--sdas/compliance-check)<a href="https://agentmods.dev/skills/tahirraufkeeyu/software-development-agent-stack--sdas/compliance-check"><img src="https://agentmods.dev/badge/skills/tahirraufkeeyu/software-development-agent-stack--sdas/compliance-check/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/tahirraufkeeyu/software-development-agent-stack--sdas/compliance-check"><img src="https://agentmods.dev/badge/skills/tahirraufkeeyu/software-development-agent-stack--sdas/compliance-check.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 | $0.00074 | $0.01750 |
| Opus 5 | $0.00037 | $0.00875 |
| Sonnet 5 | $0.00015 | $0.00350 |
| Haiku 4.5 | $0.00007 | $0.00175 |
Grade A, and why
compliance-check 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.
How it starts
The opening of the file, as written. The whole thing — 174 lines — stays where its author put it; the contents beside it link to each section on GitHub.
When to use
Trigger on any of:
- "Prep for SOC 2 Type II" / "ISO 27001 gap analysis" / "evidence bundle".
- Quarterly compliance check cadence.
- Auditor requested a control matrix or walkthrough deck.
- Investor/customer security questionnaire needs underlying evidence.
Do not use this for HIPAA, PCI-DSS, or FedRAMP — those require specialised control sets. This skill covers SOC 2 TSC + ISO 27001 Annex A.
Inputs
FRAMEWORK—soc2oriso27001orboth(default:soc2).EVIDENCE_DIR— directory containing collected evidence artefacts (logs, config exports, screenshots, policy PDFs). Required.ORG_META— YAML with org name, fiscal period, scope boundary, owner map.OUT_DIR(default:./compliance-out).- Optional env:
JIRA_PROJECT— if set, gap tickets are emitted as Jira-create JSON.TICKET_FORMAT—jira|github|markdown(default:markdown).
Example ORG_META:
org: "Acme Corp"
scope:
systems: ["app-production", "data-warehouse", "corp-it"]
regions: ["us-east-1", "eu-west-1"]
period:
type: "type2"
start: "2026-01-01"
end: "2026-12-31"
owners:
CC1: "People Ops"
CC2: "Security Eng"
CC3: "Security Eng"
CC4: "Security Eng"
CC5: "IT"
CC6: "Security Eng"
CC7: "SRE"
CC8: "Engineering"
CC9: "Legal / Risk"
Outputs
control-matrix.csv— one row per control:id, title, framework, owner, evidence_paths, design_ok, operating_ok, gap_summary.gaps.json— machine-readable gap list.gap-tickets.{md,json}— ready-to-paste ticket list.compliance-summary.md— executive-level summary with readiness score.
Tool dependencies
yq+jq.pandoc(optional) — to export the evidence bundle as a PDF dossier.- No external SaaS dependency; the skill is offline-first.
Procedure
- Parse
ORG_METAand validate required fields (org, scope, period, owners map covers every CC / Annex A domain). - Build the control inventory:
- SOC 2: load
references/soc2-controls.mdand parse the table into a list of 64+ control points (CC1.1 - CC9.2, plus A, C, P categories if the period includes availability/confidentiality/privacy). - ISO 27001: parse Annex A 2022 (93 controls across 4 themes: Organizational, People, Physical, Technological).
- SOC 2: load
- Walk
$EVIDENCE_DIRand catalog each artefact:{path, sha256, type, period_covered, collected_at}. Types includepolicy,config_export,log_sample,screenshot,ticket_link,training_record,access_review,vulnerability_scan. - Map evidence to controls via the
evidence_typeslist inreferences/soc2-controls.md(e.g. CC6.1 requiresaccess_review+identity_provider_config+mfa_enforcement_proof). - Assess each control:
- Design (ToD): are the required artefact types present?
- Operating effectiveness (ToE): do the artefact(s) cover the period with sufficient sampling (e.g. quarterly access reviews for a Type II year)?
- Score:
pass|partial|fail|not_applicable.
- Produce gap list: any
partialorfailbecomes a gap with remediation steps drawn from the "Common deficiencies" column. - Emit tickets in the requested format:
- Markdown:
- [ ] [CC6.1] Quarterly access review missing for EU region — owner: Security Eng — target: 2026-06-30. - Jira JSON: fields
project,summary,description,priority,labels,components. - GitHub issue JSON:
title,body,labels,assignees.
- Markdown:
- Write
compliance-summary.md:- Readiness score:
passed_controls / total_controls. - Gap counts by severity (P0 blocking, P1 required, P2 nice-to-have).
- Top 10 gaps by risk.
- Framework coverage table.
- Readiness score:
What ships with it
1 file 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.
- 10d ago First seen · 174 lines · 74 tokens per session scan A 7d4e498134d6
compliance-check is a skill published in the GitHub repository tahirraufkeeyu/software-development-agent-stack--sdas (18 stars, last pushed 4mo ago), licensed MIT. It adds 74 tokens to every session and 1,750 once invoked, about $0.0004 per session on Opus 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 skills, from other repositories
specification-writing
A workflow for writing complete patent specifications from patent claims and an invention disclosure. It adapts the document to a chosen jurisdiction, such as the US, Europe, or China.
regulatory-research-fallback
Fallback workflow for regulatory research when web extraction tools fail on government PDFs.
x-scorecard
OpenSSF Scorecard for assessing open source project security. Check security best practices and compliance. Dependency: This is an x-cmd module. Install x-cmd first (see x-cmd skill for installation options). see x-cmd skill for installation.
gesellschaftsrechtliche-satzungen-agb
Für Gesellschaftsrechtliche Satzungen AGB Abgrenzung: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt. Fachgebiet: AGB-Recht-Prüfer. Route: gesellschaftsrechtliche-satzungen-agb.
memstack-business-gdpr
Use this skill when the user says 'GDPR', 'data protection', 'privacy compliance', 'DPA', 'DSAR', 'data subject request', 'cookie consent', 'privacy audit', 'CCPA', or asks 'do I need GDPR for this repo'. Scans the repository to detect what personal data is collected, classifies sensitivity, determines whether GDPR…
nda-review
Use when the user uploads or pastes a non-disclosure agreement and asks for review, redline, risk assessment, or a recommendation on whether to sign. Identifies missing standard protections, one-sided or unusual provisions, and operational issues; produces a structured report with severity ratings and citations to…