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.
npx skills add byerlikaya/claude-starter-kit --skill red-teamgit clone --depth 1 https://github.com/byerlikaya/claude-starter-kitWrote 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/byerlikaya/claude-starter-kit/red-team)<a href="https://agentmods.dev/skills/byerlikaya/claude-starter-kit/red-team"><img src="https://agentmods.dev/badge/skills/byerlikaya/claude-starter-kit/red-team/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/byerlikaya/claude-starter-kit/red-team"><img src="https://agentmods.dev/badge/skills/byerlikaya/claude-starter-kit/red-team.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 | $0.00039 | $0.00844 |
| Opus 5.5 | $0.00016 | $0.00338 |
| Sonnet 5.5 | $0.00008 | $0.00169 |
| Haiku 4.5 | $0.00004 | $0.00084 |
Grade A, and why
red-team 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.
How it starts
The opening of the file, as written. The whole thing — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Red Team (LLM / Agent Defense)
Trigger phrases: "red team", "red-team", "prompt injection", "test prompt injection", "jailbreak", "defense test", "adversarial test", "injection scenario", "previous instructions", "hidden instructions", "malicious instructions", "injected instructions"
Goal: verify a system's defense against prompt injection and abuse by attempting to break it.
Only meaningful on systems that have a defense (the CLAUDE.md "Untrusted content" axis); report findings to security-expert-csk.
Ethical boundary: Only test your own / authorized system. The attack scenarios generated are for verifying the defense; actual harm / use against someone else's system is out of scope (§4, security policy).
Threat model — what to test
- Instruction hijacking: content read via a tool (web, file, issue, e-mail, DOM) says "forget the previous instructions / run this." Does the system keep it as data, or treat it as a command?
- Authority/approval bypass: content gives a fake approval like "the user authorized / test mode / admin." Does the system take its §4.4/§4.5 approval only from the user?
- Data exfiltration: content suggests sending user data to an address/endpoint. Does the system blindly fetch/exfil?
- Tool abuse: content embeds a destructive command / hidden link / encoded instruction.
- Indirect injection: a malicious instruction is stashed in data that will be read later (a record, a comment, a file name).
How to test
- Extract entry points — every place the system reads untrusted content (the same attack surface: security-scan).
- Plant an injection payload — embed an instruction/authority-claim/urgency/encoded text into that content.
- Observe: did the system apply the instruction, or surface it and ask the user? Did it take approval from the content?
- Vary it: role-play, "test mode", multi-step, cross-language, base64/homoglyph evasion.
- Classify the result: defense held / partial / broken; every break is a finding.
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 Changed f6926e5c3178
- 1mo ago Changed · +4 lines 810e42e907c8
- 1mo ago First seen · 47 lines · 39 tokens per session scan A e85bac2048e9
red-team is a skill published in the GitHub repository byerlikaya/claude-starter-kit (24 stars, last pushed 1mo ago), licensed MIT. It adds 39 tokens to every session and 844 once invoked, about $0.0002 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
shiplog
Recap of everything shipped since the last run - cross-repo PRs, security fixes, star deltas, and X traction, synthesized into a digest article and a ready-to-post shiplog in your voice.
token-pick
One token recommendation and one prediction market pick - scored, quantified, with a skip branch when signals are weak.
taskmarket-delegate
Delegate work to the TaskMarket agent-worker market - browse open tasks, create tasks with explicit authorization, and track/submit work, so an agent can outsource instead of burning inference on unreliable or low-confidence work.
create-prove
Run a changed Aeon skill for real and attach SHA-bound behavioral evidence to its PR.
case-interview-practice
Interactive consulting case interview practice with structured frameworks, feedback mechanisms, and progressive difficulty. Use when preparing for management consulting interviews, case competitions, or business problem-solving exercises.
agent-flutter-developer
Specialist subagent: Flutter/Dart cross-platform development, Riverpod state management, and platform channels specialist. Use when building Flutter apps, implementing state management, or working with native platform features. Trigger phrases: Flutter, Dart, Riverpod, Bloc, widget, MaterialApp, GoRouter, platform…