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/dodobrands/peekie/agents-mdgit clone --depth 1 https://github.com/dodobrands/PeekieWrote 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/dodobrands/peekie/agents-md)<a href="https://agentmods.dev/instructions/dodobrands/peekie/agents-md"><img src="https://agentmods.dev/badge/instructions/dodobrands/peekie/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 5.1 | $0.01456 | $0.01456 |
| Opus 5 | $0.00728 | $0.00728 |
| Sonnet 5 | $0.00291 | $0.00291 |
| Haiku 4.5 | $0.00146 | $0.00146 |
Grade A, and why
Peekie 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 6d 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 — 190 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Project Overview
Peekie is a Swift package that parses .xcresult files generated by Xcode to produce structured reports of build and test results. It provides programmatic access to test cases, code coverage, and warnings for CI/CD pipelines and automated scripts.
Development Commands
Building
swift build
Testing
# Run all tests
swift test
# Run a specific test
swift test --filter <TestClassName>.<testMethodName>
Linting
The project uses nicklockwood/SwiftFormat for code formatting and realm/SwiftLint for semantic checks. Both are pinned via mise (mise.toml).
# Install (or update) toolchain
mise install
# Format the codebase in place
swiftformat .
# CI-equivalent strict checks (run before pushing)
swiftformat --lint .
swiftlint --strict
Configuration: .swiftformat and .swiftlint.yml at repo root. Periphery still runs for unused-code detection:
periphery scan --skip-build --strict
CI runs SwiftFormat (--lint), SwiftLint (--strict), and Periphery in a separate Lint workflow that must pass before merging to main.
Running the Command-Line Tool
swift run peekie list path/to/tests.xcresult
Options:
<xcresult-path>: Path to the.xcresultfile (positional argument)--include: Filter test results by status (e.g.,failure,skipped)
Architecture
Core Components
Report (Sources/PeekieSDK/Models/Report.swift)
- Primary data model representing parsed
.xcresultdata - Hierarchical structure:
Module→File→RepeatableTest→Test - Each test has a status (success, failure, expectedFailure, skipped, mixed, unknown) and duration
- Provides coverage data and filtering capabilities
Shell (Sources/PeekieSDK/shell.swift)
- Executes shell commands via
/bin/zsh - Used internally to invoke
xcrun xcresulttoolandxcrun xccovfor parsing.xcresultfiles
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.
- 6d ago First seen · 190 lines · 1,456 tokens per session scan A 1f3f49ddc4e4
Peekie AGENTS.md is an instructions file published in the GitHub repository dodobrands/Peekie (32 stars, last pushed 5d ago), licensed Apache-2.0. It adds 1,456 tokens to every session, about $0.0073 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
Swift-Testing-Agent-Skill copilot-instructions.md
Instructions for AvdLee/Swift-Testing-Agent-Skill, covering core agent skills principles, format compliance, skill content organization (progressive disclosure), review focus areas and common issues to flag.
SwiftUIShaders AGENTS.md
Instructions for krispuckett/SwiftUIShaders, covering agents.md: architecture for coding agents, what this package is, how swiftui metal shader effects work (the mental model), how to add a new shader and how to modify an existing shader.
SwiftUIShaders CLAUDE.md
Instructions for krispuckett/SwiftUIShaders: This package's working guide for AI agents lives in AGENTS.md. Read it before extending, modifying, or rebuilding the shaders.
Swift-Concurrency-Agent-Skill copilot-instructions.md
Instructions for AvdLee/Swift-Concurrency-Agent-Skill, covering github copilot instructions: agent skills expert, core agent skills principles, format compliance, skill content organization and review focus areas.
liney AGENTS.md
AGENTS.md instructions for everettjf/liney, covering liney repository collaboration guide, 交流语言 / communication language, project overview, repository layout and build and test.
MarkdownView AGENTS.md
Instructions for keitaoouchi/MarkdownView, covering agents, technical components, relationships (data/event flow overview), extension points (overview) and platform / distribution.