fsd-owasp-reader

fsd-owasp-reader is an agent for Claude Code from IncommensurableHubris/fullstack-director. It costs 104 tokens per session (524 once invoked), scanned A, original, MIT.

A read-only security review agent that examines one assigned area of a codebase using OWASP guidance. OWASP is a project that publishes common web-application security risks.

In plain words
What is it for?
It reviews a specific security slice, may run relevant scanners, and reports confirmed issues with file and line evidence.
Why use it?
It provides evidence-based findings without changing code or searching outside its assigned area.

Agent for Claude Code

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.

agentmods
npx agentmods add agents/incommensurablehubris/fullstack-director/fsd-owasp-reader
Clone the repo
git clone --depth 1 https://github.com/IncommensurableHubris/fullstack-director

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 fsd-owasp-reader

README.md
[![agentmods](https://agentmods.dev/badge/agents/incommensurablehubris/fullstack-director/fsd-owasp-reader.svg)](https://agentmods.dev/agents/incommensurablehubris/fullstack-director/fsd-owasp-reader)
Your own site
<a href="https://agentmods.dev/agents/incommensurablehubris/fullstack-director/fsd-owasp-reader"><img src="https://agentmods.dev/badge/agents/incommensurablehubris/fullstack-director/fsd-owasp-reader.svg" alt="Measured on agentmods" height="20"></a>
Per session 104 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 524 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00104 $0.00524
Opus 5 $0.00052 $0.00262
Sonnet 5 $0.00021 $0.00105
Haiku 4.5 $0.00010 $0.00052

Measured 4d ago against content hash 11457da2994b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

fsd-owasp-reader 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 4d 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.

.claude/agents/fsd-owasp-reader.md · 30 lines

What it actually says

You are one blind reader in the Fullstack Director security panel — the spawn-branch realization of shared/subagent-protocol.md § parallel readers + synthesizer. The 07 seat spawns 4 (+1 conditional) of you in parallel; each spawn sees only its own remit.

Seed (from your prompt ONLY): your area-slice (e.g. "R2 · Injection & Forgery — A03/A10 + output handling", or an agentic-panel slice under Profile: agent-system) + the code paths in scope + the audit context paths the seat names. You are blind to the other readers — do not speculate about their areas or read outside your slice.

Stance — neutral, evidence-required: analyze the code; do not hunt to please. "Find the vulnerability" framing inflates false positives; a finding exists only when you can cite the file:line and the tainted source/sink (source_quote). A behavior claim without one is an inference, not a finding. Never reproduce a secret VALUE — quote with the value redacted, env-var names only.

You may run your area's deterministic scanners via Bash where available (npm audit / osv-scanner / gitleaks / semgrep — availability recorded, absence never silently skipped). You never edit code or write files — the synthesizer and the 07 seat own the report.

Return ONLY: your area label · the findings list (each: file:line · source_quote · proposed_severity · OWASP area tag) · the scanners run (or recorded-absent) · and the line read-only: no file written; slice: <area> — the synthesizer de-dupes by target, takes max severity, and preserves your quotes.

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. 4d ago First seen · 30 lines · 104 tokens per session scan A 11457da2994b

Subscribe to this mod's changes

fsd-owasp-reader is an agent published in the GitHub repository IncommensurableHubris/fullstack-director (5 stars, last pushed 24d ago), licensed MIT. It adds 104 tokens to every session and 524 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.

Related

Other agents, from other repositories

gsd-phase-researcher

Researches how to implement a phase before planning. Produces RESEARCH.md consumed by gsd-planner. Spawned by /gsd:plan-phase orchestrator.

open-gsd/gsd-core · 41 tokens

Technical Writer

Technical writer who produces developer-facing documentation — API references, getting-started guides, deployment runbooks, troubleshooting.

dinhnguyenngoc/spec-driven-claude-code · 24 tokens

integration-verifier

Verifies that the tasks of a completed build actually wire together. Dispatched once at /execute Step 4 for multi-task specs. Read-only -- cannot modify the codebase. Checks cross-task wiring + global acceptance, not per-task acceptance.

dwarvesf/dwarves-kit · 53 tokens

planner

Drafts the execution Plan (plan.md) AND emits task records for a SpecManager feature, grounded in the approved Architecture and the existing codebase. Plans MUST be organised into phases with Fibonacci-scored tasks ≤3.

joanseg/specmanager · 46 tokens

data-etl-worker

Implements a data pipeline/transform task, extract/transform/load, parsing, dedup, normalization. Write-capable; prefers DuckDB SQL for the transform per the house stack. Dispatched by /kit:execute step 2b-0 as the data-etl domain implementer.

dwarvesf/dwarves-kit · 64 tokens

frontend-reviewer

Reviews a diff through the FRONTEND lens only (a11y/ARIA, semantic HTML, focus/keyboard, state handling, responsive/viewport, color-only signaling). Read-only. Dispatched by /kit:review-team as the frontend domain lens when the diff touches UI.

dwarvesf/dwarves-kit · 60 tokens