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 agentmods add skills/cognisn/cloudledger/security-assessmentnpx skills add Cognisn/cloudledger --skill security-assessmentgit clone --depth 1 https://github.com/Cognisn/cloudledgerWrote 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/cognisn/cloudledger/security-assessment)<a href="https://agentmods.dev/skills/cognisn/cloudledger/security-assessment"><img src="https://agentmods.dev/badge/skills/cognisn/cloudledger/security-assessment.svg" alt="Measured on agentmods" 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 | $0.00097 | $0.00785 |
| Opus 5 | $0.00048 | $0.00392 |
| Sonnet 5 | $0.00019 | $0.00157 |
| Haiku 4.5 | $0.00010 | $0.00078 |
Grade A, and why
security-assessment 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 3d 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 — 87 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Security assessment
Turn the CloudLedger server's raw findings into a scored, written security assessment of a scanned AWS account.
The server returns deterministic evidence with advisory severities and a
coverage report; it does not compute a score. This skill supplies the scoring
methodology (references/scoring-rubric.md) and the report
(references/report-template.md). The score is computed here, by the rubric —
not by the server.
Workflow
Follow these steps in order.
1. Confirm the server is available
The tools get_security_assessment_data, analyze_service_exposure and
get_security_check_catalogue must be reachable. If they are not, stop and tell
the user the CloudLedger server is not connected — do not produce a partial
report.
2. Resolve the scan
Use the latest scan unless the user names a scan_id. Call list_scans and
get_scan_summary if helpful, and state explicitly which account and scan date
you are assessing before continuing.
3. Learn the catalogue
Call get_security_check_catalogue. Its count and check list are the
authoritative set of applicable checks for the coverage calculation. If a check
appears in results that is not in references/check-interpretation.md, handle
it gracefully using its server-supplied recommendation rather than dropping
it.
4. Gather findings
Call get_security_assessment_data with no category filter. Keep categories,
not_evaluated, and prowler.
5. Gather exposure
Call analyze_service_exposure with no service filter. Keep the four service
results and their evidence chains.
6. Gather Prowler detail (only if present)
If prowler.available is true, call get_prowler_findings with
summary_mode: true for the corroboration section. If false, skip it entirely.
7. Score
Apply references/scoring-rubric.md exactly. Compute category sub-scores, the
overall score, grade, and coverage. If Prowler is present, compute both native
and blended scores. Show the working.
What ships with it
4 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.
- 3d ago First seen · 87 lines · 0 tokens per session scan A f027c495489f
security-assessment is a skill published in the GitHub repository Cognisn/cloudledger (0 stars, last pushed 15d ago), licensed MIT. It adds 97 tokens to every session and 785 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
aws-cloud-penetration-testing
Penetration test AWS cloud environments for misconfigurations, privilege escalation, data exposure, and lateral movement. Use this skill when assessing AWS accounts for security weaknesses including S3 bucket misconfigurations, IAM policy flaws, EC2 metadata exploitation, Lambda function abuse, and cross-account…
conducting-cloud-infrastructure-penetration-test
Perform a cloud infrastructure penetration test across AWS, Azure, and GCP to identify IAM misconfigurations, exposed storage buckets, insecure serverless functions, and cloud-native attack paths using Pacu, ScoutSuite, and Prowler.
aws-cloud-penetration-testing
Penetration test AWS cloud environments for misconfigurations, privilege escalation, data exposure, and lateral movement. Use this skill when assessing AWS accounts for security weaknesses including S3 bucket misconfigurations, IAM policy flaws, EC2 metadata exploitation, Lambda function abuse, and cross-account…
conducting-cloud-infrastructure-penetration-test
Perform a cloud infrastructure penetration test across AWS, Azure, and GCP to identify IAM misconfigurations, exposed storage buckets, insecure serverless functions, and cloud-native attack paths using Pacu, ScoutSuite, and Prowler.
agentcore-investigation
Investigate Bedrock AgentCore runtime sessions via CloudWatch Logs Insights — resolve session/trace IDs, query OTEL spans, filter noise, build timelines. Use when debugging AgentCore agent sessions, tracing tool calls, or analyzing latency.
amazon aurora dsql
Deprecated compatibility redirect for Aurora DSQL guidance. Use when a request concerns DSQL, Aurora DSQL, distributed SQL, DSQL schemas, migrations, queries, authentication, performance, or application development.