orchestrator: Skill for Claude Code

.claude/skills/security-test-doc-gen/SKILL.md

security-test-doc-gen is a skill for Claude Code from c9r-io/orchestrator. It costs 54 tokens per session (1,416 once invoked), scanned A, original, MIT.

A workflow for creating reusable security test documents under docs/security/ from the current project and its confirmed plans. It uses OWASP ASVS 5.0, a security verification standard, as the control source.

In plain words
What is it for?
Use it to add or complete security scenarios, map them to applicable ASVS requirements, and document how each scenario can be tested.
Why use it?
It turns a generic security template into project-specific, reproducible test scenarios with traceable evidence, without claiming certification.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: reads .claude/ paths.

This is c9r-io/orchestrator's own configuration. It tells Claude Code how to work on orchestrator itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything orchestrator configures →

Reuse

Borrowing it

Nothing to install: this file belongs to c9r-io/orchestrator. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/c9r-io/orchestrator/main/.claude/skills/security-test-doc-gen/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/c9r-io/orchestrator

Made for: Claude Code.

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 security-test-doc-gen

README.md
[![agentmods](https://agentmods.dev/badge/skills/c9r-io/orchestrator/security-test-doc-gen/github.svg)](https://agentmods.dev/skills/c9r-io/orchestrator/security-test-doc-gen)
Your own site
<a href="https://agentmods.dev/skills/c9r-io/orchestrator/security-test-doc-gen"><img src="https://agentmods.dev/badge/skills/c9r-io/orchestrator/security-test-doc-gen/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 security-test-doc-gen

Your own site · 80×15
<a href="https://agentmods.dev/skills/c9r-io/orchestrator/security-test-doc-gen"><img src="https://agentmods.dev/badge/skills/c9r-io/orchestrator/security-test-doc-gen.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 54 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,416 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00054 $0.01416
Opus 5 $0.00027 $0.00708
Sonnet 5 $0.00011 $0.00283
Haiku 4.5 $0.00005 $0.00142

Measured 10d ago against content hash a19581fa664e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

security-test-doc-gen scanned grade A with 1 finding 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.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/extract_surface.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- Add a runnable verification method per scenario (curl/grpcurl/SQL/log grep)
.claude/skills/security-test-doc-gen/SKILL.md · 107 lines

How it starts

The opening of the file, as written. The whole thing — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Security Test Doc Gen

Generate/complete docs/security/** so it evolves from a generic template into a set of project-aligned, reproducible, executable security test scenarios.

ASVS 5.0 High Bar (Required)

  • Baseline: Use OWASP ASVS 5.0 as the control source. Default target is L2 unless the project explicitly targets L1, or a high-value system requires L3.
  • No "fake compliance": Docs may claim "covered chapters/requirements + evidence", but must not claim "ASVS certified/passed".
  • Traceability: Each doc header must list applicable OWASP ASVS 5.0 chapters (and requirement ids if needed). Record selection rationale and evidence sources in docs/security/_surface/asvs_profile.md.
  • Do not invent requirement ids: If you reference a specific requirement id, it must match ASVS 5.0 text.
    • Recommended format: v5.0.0-<chapter>.<section>.<requirement>

Inputs

  • Current repo code and configuration (core/, crates/, gui/, .github/, and any deployment assets that actually exist)
  • If available: a confirmed plan mode output (to cover new security scenarios introduced by new features)

Outputs

  • Update/add docs/security/** (only the portions that apply to the current project)
  • Update docs/security/README.md index (keep it lightweight; do not hardcode totals)

Workflow

  1. Define scope

    • feature-only: only cover security scenarios relevant to the current feature (recommended default)
    • system-baseline: establish/refresh a baseline across the whole project (pre-release/security regression)
    • Decide the ASVS target level (default L2) and record it in docs/security/_surface/asvs_profile.md
  2. Discover the security surface (from code/config)

    • Prefer running the extraction script to produce a "security surface inventory" (endpoints/routes/services):
      • .claude/skills/security-test-doc-gen/scripts/extract_surface.sh
      • Output defaults to docs/security/_surface/
      • Optional overrides:
        • CORE_DIRS=core,auth9-core (backend candidates, comma-separated)
        • PORTAL_DIRS=portal,auth9-portal (frontend candidates, comma-separated)
      • If output is empty: routes may be generated or live outside the extractor's defaults; fall back to manual searches across core/, crates/, and gui/.
    • HTTP API:
      • Search for router definitions (framework-specific) and /api/ paths
      • If OpenAPI/Swagger exists, use it as the endpoint inventory source
    • gRPC:
      • Search for .proto files and service definitions
    • Authentication:
      • Search for Authorization, Bearer, jwt, oidc, session, cookie
    • Authorization model:
      • Search for rbac, permission, role, tenant, org, and Workspace authorization concepts.
    • Outbound calls:
      • Search for HTTP client usage and URL fields (SSRF scenarios)
    • File handling:
      • Search for upload/download endpoints, multipart handling, object storage
    • Data stores and secrets:
      • Search for sqlx/redis/DATABASE_URL/REDIS_URL/SECRET, etc.

Read the full file on GitHub · 107 lines

Files

What ships with it

6 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.

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 · 107 lines · 54 tokens per session scan A a19581fa664e

Subscribe to this mod's changes

security-test-doc-gen is a skill published in the GitHub repository c9r-io/orchestrator (21 stars, last pushed 8d ago), licensed MIT. It adds 54 tokens to every session and 1,416 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.