orca-config-origin

orca-config-origin is a skill for Claude Code from orcasecurity/orca-skills. It costs 83 tokens per session (6,761 once invoked), scanned A, original, MIT.

An investigation that traces a cloud-security alert back to its origin. It identifies who changed the resource, how it was deployed, what introduced the problem, and when each event happened.

In plain words
What is it for?
Investigating Orca alerts, finding the responsible identity or account, identifying whether Terraform, CloudFormation, Pulumi, a console, CLI, or another method made the change, and locating the source that should be corrected.
Why use it?
It helps explain the cause of an alert instead of only showing the current misconfiguration or vulnerability. This makes it easier to fix the source and identify ownership.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the orca-skills plugin — 19 skills shipped together

Good fit Investigating Orca alerts, finding the responsible identity or account, identifying whether Terraform, CloudFormation, Pulumi, a console, CLI, or another method made the change, and locating the source that should be corrected.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/orcasecurity/orca-skills/orca-config-origin
Install

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.

Any agent
npx skills add orcasecurity/orca-skills --skill orca-config-origin
Clone the repo
git clone --depth 1 https://github.com/orcasecurity/orca-skills

Made for: Claude Code.

Or install orca-skills, the plugin that ships this one along with the rest of its 19 skills.

Wrote 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.

agentmods badge for orca-config-origin

README.md
[![agentmods](https://agentmods.dev/badge/skills/orcasecurity/orca-skills/orca-config-origin/github.svg)](https://agentmods.dev/skills/orcasecurity/orca-skills/orca-config-origin)
Your own site
<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.

agentmods 80×15 button for orca-config-origin

Your own site · 80×15
<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>
Per session 83 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 6,761 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 10d ago against content hash c30d9a952b8e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

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.

skills/orca-config-origin/SKILL.md · 687 lines

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:

  1. Who created or modified the resource (identity, role, account)
  2. How it was deployed (Terraform, CloudFormation, Pulumi, CDK, Console, CLI, SDK)
  3. What introduced the specific issue (the IaC code, AMI, container image, user action, or automation that caused the alert)
  4. When — a full timeline from resource creation → issue introduction → alert detection
  5. 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:

Read the full file on GitHub · 687 lines

Changes

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.

  1. 10d ago First seen · 687 lines · 83 tokens per session scan A c30d9a952b8e

Subscribe to this mod's changes

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.