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 orcasecurity/orca-skills --skill orca-config-origingit clone --depth 1 https://github.com/orcasecurity/orca-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/orcasecurity/orca-skills/orca-config-origin)<a href="https://agentmods.dev/skills/orcasecurity/orca-skills/orca-config-origin"><img src="https://agentmods.dev/badge/skills/orcasecurity/orca-skills/orca-config-origin/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/orcasecurity/orca-skills/orca-config-origin"><img src="https://agentmods.dev/badge/skills/orcasecurity/orca-skills/orca-config-origin.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00083 | $0.06761 |
| Opus 5 | $0.00042 | $0.03381 |
| Sonnet 5 | $0.00017 | $0.01352 |
| Haiku 4.5 | $0.00008 | $0.00676 |
Grade A, and why
orca-config-origin 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 — 687 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Orca Config Origin Skill
Answers the question: "Who did this, how was it deployed, and what introduced the issue?"
Given any Orca alert (misconfiguration, vulnerability, sensitive data, or anomaly), traces back through cloud audit logs, Orca CodeOrigins, and asset metadata to find:
- Who created or modified the resource (identity, role, account)
- How it was deployed (Terraform, CloudFormation, Pulumi, CDK, Console, CLI, SDK)
- What introduced the specific issue (the IaC code, AMI, container image, user action, or automation that caused the alert)
- When — a full timeline from resource creation → issue introduction → alert detection
- Where — source code file, CI/CD pipeline, or manual action that should be fixed
Usage
/orca-config-origin <alert-id>
/orca-config-origin orca-3380725
Or natural language:
- "who created this misconfiguration? orca-3380725"
- "trace back orca-3511464"
- "where did this config come from? orca-3364845"
- "find the owner of orca-3213766"
Processing Logic
Step 1: Understand the Alert and Resource
Fetch the alert with get_alert and extract:
- Asset type (e.g., AwsUser, GcpUser, AwsS3Bucket, AzureVm)
- Asset identifiers: ARN, name, unique ID, account/project
- Cloud provider: AWS, Azure, GCP (determines which audit log to query)
- Misconfiguration details: What setting is wrong (e.g., MFA disabled, public access, overprivileged role)
- Alert creation date: When Orca first detected this
Also fetch the asset with get_asset_by_id (using the asset_unique_id or group_unique_id, with model_type matching the asset type) for additional context:
- Tags (often contain
owner,team,environment,terraform,stack-name) - Creation timestamp
- Configuration details
- CodeOrigins — if present, this contains the exact IaC source code (repo, file, line numbers, git blame). This is the strongest possible origin signal.
Alert Category → Origin Strategy
The origin of the issue depends on the alert type. Classify first, then trace differently:
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 · 687 lines · 83 tokens per session scan A c30d9a952b8e
orca-config-origin is a skill published in the GitHub repository orcasecurity/orca-skills (49 stars, last pushed 3d ago), licensed MIT. It adds 83 tokens to every session and 6,761 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
ml-pipeline-workflow
Build end-to-end MLOps pipelines from data preparation through model training, validation, and production deployment. Use when creating ML pipelines, implementing MLOps practices, or automating model training and deployment workflows.
netlify-deploy
Deploy web projects to Netlify using the Netlify CLI (npx netlify). Use when the user asks to deploy, host, publish, or link a site/repo on Netlify, including preview and production deploys.
public-web-deploy
Publish a public website safely: DNS, web server, HTTPS, hardening, verify. Routes raw dev servers through nginx/Caddy/Apache/Cloudflare Pages.
game-pipeline
Game lifecycle orchestrator: scaffold, assets, audio, QA, deploy.
service-health-check
Service health monitoring, endpoint validation, and CVE source auditing.
docker-devops
Docker/K8s: Dockerfile, multi-stage, compose, manifests, Helm. Triggers: Docker, Dockerfile, container, Kubernetes, k8s, compose, Helm, pod.