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 agentmods add skills/madappgang/magus/securitynpx skills add MadAppGang/magus --skill securitygit clone --depth 1 https://github.com/MadAppGang/magusWrote 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/madappgang/magus/security)<a href="https://agentmods.dev/skills/madappgang/magus/security"><img src="https://agentmods.dev/badge/skills/madappgang/magus/security.svg" alt="Measured on agentmods" 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 | $0.00049 | $0.02379 |
| Opus 5 | $0.00024 | $0.01189 |
| Sonnet 5 | $0.00010 | $0.00476 |
| Haiku 4.5 | $0.00005 | $0.00238 |
Grade A, and why
security scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Security for Bun services
Bun ships strong primitives natively — argon2id via Bun.password, an OS-keychain API in
Bun.secrets, bun audit, Bun.escapeHTML, full node:crypto. The bugs are almost never in
those primitives. They are in the policy around them: comparing a token with ===, hashing an API
key with argon2, a rate limiter keyed on a header the attacker controls, a CORS policy that
reflects any origin.
This skill ships that policy as tested code (51 tests, tsc --noEmit clean, Bun 1.3.10).
Copy the guards in
SKILL="${CLAUDE_PLUGIN_ROOT:+$CLAUDE_PLUGIN_ROOT/skills/security}"; SKILL="${SKILL:-PASTE_THE_DIR_THIS_SKILL_MD_WAS_READ_FROM}" # that var is UNSET in a Bash tool (MEASURED) — so paste it. `:?` would ABORT the block and copy nothing
mkdir -p src; if [ -d "$SKILL/assets" ]; then cp -r "$SKILL/assets/security" src/security # credentials + guards + 2 test files
else echo "SKILL is still the placeholder — paste the real dir above and re-run"; fi
| Export | Purpose |
|---|---|
hashPassword / verifyPassword / needsRehash |
argon2id with the right cost, plus in-place migration |
generateToken / hashToken / verifyToken |
CSPRNG tokens, fast hashing, constant-time verify |
safeEqual |
constant-time compare that survives length mismatch |
authenticate |
login with no user-enumeration timing oracle |
redact |
strip secrets before anything reaches a log |
RateLimiter / rateLimitHeaders / clientKey |
limiting that cannot be bypassed by a forged header |
securityHeaders / corsHeaders |
strict defaults, no wildcard origin possible |
Two hashing costs, and using the wrong one is the bug
| Secret | Entropy | Hash with | Why |
|---|---|---|---|
| user password | low | argon2id (Bun.password) |
slow hashing is the only defence against offline brute force |
| session id, API key | 256-bit random | SHA-256 | cannot be brute-forced; argon2 here taxes every request for nothing |
What ships with it
10 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.
- assets/security/credentials.test.ts 8.7 KB runs code
- assets/security/credentials.ts 5.7 KB runs code
- assets/security/guards.test.ts 7.6 KB runs code
- assets/security/guards.ts 7.6 KB runs code
- bun.lock 1.1 KB
- package.json 377 B
- references/authn-authz.md 5.9 KB
- references/injection-and-input.md 6.5 KB
- references/supply-chain.md 5.2 KB
- tsconfig.json 324 B
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.
- 5d ago First seen · 170 lines · 49 tokens per session scan A 6d7e307f2c4c
security is a skill published in the GitHub repository MadAppGang/magus (9 stars, last pushed yesterday), licensed MIT. It adds 49 tokens to every session and 2,379 once invoked, about $0.0002 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…