Borrowing it
Nothing to install: this file belongs to mdrideout/junjo. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/mdrideout/junjo/master/.agents/skills/studio-security-auth/SKILL.mdgit clone --depth 1 https://github.com/mdrideout/junjoWrote 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/mdrideout/junjo/studio-security-auth)<a href="https://agentmods.dev/skills/mdrideout/junjo/studio-security-auth"><img src="https://agentmods.dev/badge/skills/mdrideout/junjo/studio-security-auth/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/mdrideout/junjo/studio-security-auth"><img src="https://agentmods.dev/badge/skills/mdrideout/junjo/studio-security-auth.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 | $0.00035 | $0.00697 |
| Opus 5.5 | $0.00014 | $0.00279 |
| Sonnet 5.5 | $0.00007 | $0.00139 |
| Haiku 4.5 | $0.00003 | $0.00070 |
Grade A, and why
studio-security-auth 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 17d 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 — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Studio Security Auth
Use This Skill When
- The task changes or reviews API-key validation.
- The task changes or reviews browser sessions, the session cookie, or the order of authentication layers.
- The task changes or reviews internal authentication gRPC between the backend and ingestion.
- The user asks for a security review of authentication-sensitive code.
Do Not Use This Skill When
- The task is ordinary subsystem work with no authentication or security impact.
- The task merely lives near authentication code without changing the trust boundary.
Surface To Inspect
apps/studio/backend/server/src/app.rsapps/studio/backend/server/src/config.rsapps/studio/backend/server/src/features/auth/apps/studio/backend/server/src/features/evaluation_tokens/(developer access tokens and the bearer authorizer inaccess.rs)apps/studio/backend/server/src/features/cli_sign_in/(the CLI's browser sign-in: two public routes and three session routes)apps/studio/backend/server/src/features/internal_auth.rsapps/studio/ingestion/src/server/auth.rsapps/studio/ingestion/src/backend/client.rsapps/studio/proto/auth.prototooling/scripts/provision_local_studio.pytooling/scripts/validate_agent_studio_e2e.py
Workflow
- Read
apps/studio/AGENTS.mdandapps/studio/docs/adr/012-studio-authentication.md, which owns the credential families and the session decisions. Studio ADR-009 owns ingestion API-key validation. - Trace the full trust boundary: caller, credential transport, cache, layer or extractor, backend validation, and failure mode.
- Verify fail-closed behavior where it matters.
- Prefer concrete threat-model checks over generic security filler.
- Inspect active configuration and layers when deployment rules matter.
- Pair with
studio-backend-rustorstudio-ingestion-flowwhen the change crosses those subsystem boundaries. - Local E2E users are explicit setup-API actions, never runtime or schema
seeds.
apps/studio/TESTING.mdowns reset and validation procedures. - For repository-local stack setup, persistent development credentials, or
example environment preparation, use
junjo-local-developmentand its owning runbook.
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.
- 17d ago Changed · +10 lines · -3 tokens per session 4bbedc84e2c0
- 1mo ago First seen · 63 lines · 38 tokens per session scan A c3941ebe9921
studio-security-auth is a skill published in the GitHub repository mdrideout/junjo (20 stars, last pushed 17d ago), licensed Apache-2.0. It adds 35 tokens to every session and 697 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
ai-engineering-toolkit
6 production-ready AI engineering workflows: prompt evaluation (8-dimension scoring), context budget planning, RAG pipeline design, agent security audit (65-point checklist), eval harness building, and product sense coaching.
ai-agent-evaluation-benchmarking
Autonomous AI agent benchmark evaluation register: task completion rates, planning accuracy, tool invocation precision, and cost benchmarks.
create-tech-design
Only use when the user explicitly invokes this skill by name.
iterate-tech-design
Only use when the user explicitly invokes this skill by name.
otto-pr-review-loop
Run Polly and OCR on a PR until all findings settle.
implement-outline
Only use when the user explicitly invokes this skill by name.