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 instructions/ivan-magda/swift-security-skill/agents-mdgit clone --depth 1 https://github.com/ivan-magda/swift-security-skillWrote 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/instructions/ivan-magda/swift-security-skill/agents-md)<a href="https://agentmods.dev/instructions/ivan-magda/swift-security-skill/agents-md"><img src="https://agentmods.dev/badge/instructions/ivan-magda/swift-security-skill/agents-md.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 | $0.00844 | $0.00844 |
| Opus 5 | $0.00422 | $0.00422 |
| Sonnet 5 | $0.00169 | $0.00169 |
| Haiku 4.5 | $0.00084 | $0.00084 |
Grade A, and why
swift-security-skill AGENTS.md 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.
How it starts
The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This repository contains the Keychain & Security Expert Skill — a non-opinionated, correctness-focused reference for iOS/macOS keychain operations, biometric authentication, CryptoKit cryptography, credential lifecycle management, certificate trust, and OWASP compliance mapping.
Repo Structure
AGENTS.md ← you are here (repo-level agent onboarding)
CLAUDE.md -> AGENTS.md ← symlink for Claude Code compatibility
README.md ← human-facing documentation
LICENSE
.claude-plugin/
plugin.json ← Claude Code plugin manifest
marketplace.json ← Claude Code marketplace catalog
swift-security-expert/
SKILL.md ← the skill: router, guidelines, behavioral rules
references/
keychain-fundamentals.md ← SecItem* CRUD, query dictionaries, OSStatus
keychain-item-classes.md ← kSecClass types, composite primary keys
keychain-access-control.md ← accessibility constants, SecAccessControl
biometric-authentication.md ← keychain-bound biometrics, LAContext bypass
secure-enclave.md ← hardware-backed P256, simulator traps
cryptokit-symmetric.md ← SHA-2/3, HMAC, AES-GCM, ChaChaPoly, HKDF
cryptokit-public-key.md ← ECDSA, ECDH, HPKE, ML-KEM/ML-DSA
credential-storage-patterns.md ← OAuth tokens, API keys, refresh rotation
keychain-sharing.md ← access groups, Team ID, extensions
certificate-trust.md ← SecTrust, SPKI pinning, mTLS
migration-legacy-stores.md ← UserDefaults/plist → Keychain migration
common-anti-patterns.md ← top 10 AI-generated security mistakes
testing-security-code.md ← protocol mocks, CI/CD, Swift Testing
compliance-owasp-mapping.md ← OWASP Mobile Top 10, MASVS, MASTG
How to Use This Skill
- Start with
SKILL.md— it contains the decision tree router (review / improve / implement), core guidelines, quick reference tables, behavioral rules, and the references index. - Load reference files on demand —
SKILL.mdtells you which files to load for each query type. Do not load all 14 at once. - Follow the behavioral rules in
SKILL.md— tone calibration, output format, common AI mistakes watchlist, and scope boundaries are all defined there.
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.
- 4d ago First seen · 65 lines · 844 tokens per session scan A cc7bb3698616
swift-security-skill AGENTS.md is an instructions file published in the GitHub repository ivan-magda/swift-security-skill (31 stars, last pushed 2mo ago), licensed MIT. It adds 844 tokens to every session, about $0.0042 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 2026-08-30.
Other instructions, from other repositories
ios-agent-skill AGENTS.md
Instructions for Nagarjuna2997/ios-agent-skill, covering ios agent skill — claude ai expert ios/swift developer, when to load this skill, loading the right document, how these docs are structured and how you operate: delegation, loops, and verification.
ios-agent-skill CLAUDE.md
Instructions for Nagarjuna2997/ios-agent-skill, covering ios agent skill — claude ai expert ios/swift developer, when to load this skill, loading the right document, how these docs are structured and how you operate: delegation, loops, and verification.
ios-agent-skill GEMINI.md
Instructions for Nagarjuna2997/ios-agent-skill, covering ios agent skill — claude ai expert ios/swift developer, when to load this skill, loading the right document, how these docs are structured and how you operate: delegation, loops, and verification.
mcp-steroid CLAUDE.md
Claude Code instructions for jonnyzzz/mcp-steroid, covering claude.md, agents.md, design philosophy, recursive context lookup (do this before sub-folder work), sub-folder guides and must do.
skills CLAUDE.md
Instructions for mixedbread-ai/skills, covering mixedbread skills, repository structure, conventions, adding a new skill and testing a skill.
growmos AGENTS.md
Instructions for codician-team/growmos: This repository keeps a knowledge graph in .growmos/ (entities, typed relations, provenance, profiles, a journal). It is the shared world model that survives context windows. Treat it as memory you read at the start of work and write to as you develop. Zero-config commands.