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.
git clone --depth 1 https://github.com/IncommensurableHubris/fullstack-directorWrote 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/agents/incommensurablehubris/fullstack-director/fsd-owasp-reader)<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/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/agents/incommensurablehubris/fullstack-director/fsd-owasp-reader"><img src="https://agentmods.dev/badge/agents/incommensurablehubris/fullstack-director/fsd-owasp-reader.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00104 | $0.00524 |
| Opus 5.5 | $0.00042 | $0.00210 |
| Sonnet 5.5 | $0.00021 | $0.00105 |
| Haiku 4.5 | $0.00010 | $0.00052 |
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 1mo 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.
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.
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.
- 1mo ago First seen · 30 lines · 104 tokens per session scan A 11457da2994b
fsd-owasp-reader is an agent published in the GitHub repository IncommensurableHubris/fullstack-director (5 stars, last pushed 2mo ago), licensed MIT. It adds 104 tokens to every session and 524 once invoked, about $0.0004 per session on Opus 5.5. 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 agents, from other repositories
gsd-project-researcher
Researches domain ecosystem before roadmap creation. Produces files in .planning/research/ consumed during roadmap creation. Spawned by /gsd:new-project or /gsd:new-milestone orchestrators.
APIDesigner
Generates API contracts (OpenAPI/GraphQL) for a feature.
Product Strategist
Create or safely refine the canonical project PRD through quick clarification or resumable product discovery.
Onboarding & Environment Setup Analyst
Guides a developer through full local development environment setup — runtime tools, services, configuration, test toolchain, and verification.
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.
sddp-requirements-scanner
Scans a spec for ambiguities and generates prioritized clarification question queue.