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/bosun-ai/swiftide/agents-mdgit clone --depth 1 https://github.com/bosun-ai/swiftideWrote 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/bosun-ai/swiftide/agents-md)<a href="https://agentmods.dev/instructions/bosun-ai/swiftide/agents-md"><img src="https://agentmods.dev/badge/instructions/bosun-ai/swiftide/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 | $0.00830 | $0.00830 |
| Opus 5 | $0.00415 | $0.00415 |
| Sonnet 5 | $0.00166 | $0.00166 |
| Haiku 4.5 | $0.00083 | $0.00083 |
Grade A, and why
swiftide 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 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 — 36 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidelines
Project Structure & Module Organization
Swiftide is a Rust workspace driven by the library in swiftide/, with supporting crates such as swiftide-core/ for shared primitives, swiftide-agents/ for agent orchestration, swiftide-indexing/ and swiftide-query/ for pipeline flows, and swiftide-integrations/ for external connectors. Shared fixtures live in swiftide-test-utils/, while examples/ hosts runnable demos and benchmarks/ tracks performance scenarios. Static assets (logos and diagrams) are under images/.
Build, Test, and Development Commands
cargo check --workspace --all-featuresquickly verifies the entire workspace compiles with all feature flags enabled.cargo build --workspace --all-featurescompiles every crate and surfaces feature-gating issues early.cargo check -p swiftide-agentsis a fast way to probe agent changes before touching the rest of the workspace.cargo +nightly fmt --allapplies the reporustfmt.toml(comment wrapping requires nightly); usecargo +nightly fmt --all -- --checkto mirror CI formatting validation.cargo clippy --workspace --all-targets --all-features -- -D warningsmirrors the main lint job and keeps us aligned with the pedantic lint profile baked intoCargo.toml.cargo test -j 2 --tests --all-features --no-fail-fastmirrors the main CI test job for unit and integration tests.cargo test --doc --all-features --no-fail-fastmirrors the docs test job in CI.cargo hack check --each-feature --no-dev-depsmirrors the Cargo Hack feature-matrix check run in CI.typosmirrors the spelling check run in CI.cargo test --workspaceis still useful locally when you want a broader default test sweep; useRUST_LOG=infoif you need verbose diagnostics.- Snapshot updates flow through
cargo insta reviewafter tests rewrite.snapfiles.
Coding Style & Naming Conventions
Follow Rust 2024 idioms with four-space indentation. Public APIs should embrace builder patterns and the naming guidance from the Rust API Guidelines: snake_case for functions, UpperCamelCase for types, and SCREAMING_SNAKE_CASE constants. Avoid unsafe blocks—Cargo.toml forbids them at the workspace level. Keep comments concise so wrap_comments = true can format them within 100 columns.
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 · 36 lines · 830 tokens per session scan A a8537be19e7e
swiftide AGENTS.md is an instructions file published in the GitHub repository bosun-ai/swiftide (777 stars, last pushed yesterday), licensed MIT. It adds 830 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
omnigent copilot-instructions.md
Copilot instructions for omnigent-ai/omnigent, covering copilot code review instructions, e2e test requirement, backend test coverage and frontend test coverage.
quant-mind AGENTS.md
Instructions for LLMQuant/quant-mind, covering quantmind — agent instructions, progressive context loading, what this is, positioning and module map.
omnigent AGENTS.md
AGENTS.md instructions for omnigent-ai/omnigent, covering agent guidance, committing, local development shortcuts, pull requests and finishing a task.
terminator CLAUDE.md
Instructions for mediar-ai/terminator, covering terminator - ai-native gui automation, installation, release, or with globally installed cli and development.
quant-mind CLAUDE.md
Instructions for LLMQuant/quant-mind: CLAUDE.md imports AGENTS.md as the single source of repository instructions for coding agents. Do not duplicate rules here — edit AGENTS.md. Add Claude Code- specific guidance (if any) below the import. This block-level HTML comment is stripped from Claude's context at load, so it…
datoon CLAUDE.md
Claude Code instructions for andrii-su/datoon, covering claude.md - datoon, project overview, repository layout, source of truth and mirrored files.