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 agents/goldziher/spikard/spikard-developergit clone --depth 1 https://github.com/Goldziher/spikardWrote 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/agents/goldziher/spikard/spikard-developer)<a href="https://agentmods.dev/agents/goldziher/spikard/spikard-developer"><img src="https://agentmods.dev/badge/agents/goldziher/spikard/spikard-developer.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 | $0.00038 | $0.00674 |
| Opus 5 | $0.00019 | $0.00337 |
| Sonnet 5 | $0.00008 | $0.00135 |
| Haiku 4.5 | $0.00004 | $0.00067 |
Grade A, and why
spikard-developer 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 3d 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 — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.
spikard-developer
Workspace Structure
Cargo workspace with 15 crates:
- spikard-core: Core types (Route, Router, Method, SchemaValidator, ParameterValidator)
- spikard: Re-export facade crate
- spikard-http: Axum/tower-http server, Handler trait, middleware, auth, lifecycle hooks
- spikard-codegen: OpenAPI/GraphQL/AsyncAPI/OpenRPC code generation
- spikard-graphql: GraphQL schema, executor, and HTTP handler
- spikard-cli: CLI binary (clap-based)
- spikard-bindings-shared: Shared binding utilities
- spikard-py: Python bindings (PyO3 + pyo3-async-runtimes)
- spikard-node: Node.js bindings (napi-rs)
- spikard-rb: Ruby bindings (magnus)
- spikard-rb-macros: Ruby proc macros
- spikard-php: PHP bindings (ext-php-rs)
- spikard-elixir: Elixir bindings (rustler NIF)
Tools: tools/benchmark-harness, tools/snippet-runner, tools/test-generator
Key Patterns
- Handler trait: Language-agnostic async handler in spikard-http. All bindings implement it via Arc.
- RequestData/HandlerResponse: FFI-safe request/response types using Arc fields and serde_json::Value.
- Thin bindings: All business logic in Rust core. Bindings only convert types and forward calls.
- extension-module feature: Must NOT be in default features for spikard-py (breaks CLI binary linking).
- Fixture-driven testing: testing_data/ JSON fixtures drive tests across all language bindings.
- Tower middleware: All middleware in Rust via tower-http. Bindings expose config APIs only.
Development Workflow
task buildis core-only; usetask build:bindingsortask build:allexplicitly when bindings are neededtask test/task lint/task formatfor standard operations;task formatexcludes Alef formattingtask test:rust,task test:python,task test:node,task test:ruby,task test:phpfor per-language teststask alef:generaterunsalef all --clean --format=false; usetask alef:formatexplicitly when neededtask e2e:generate,task e2e:build,task e2e:test, andtask e2e:allfor generated e2e suitespoly lint ./poly fmt --check .enforce linting and formatting;task version:synckeeps versions aligned
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.
- 3d ago First seen · 46 lines · 38 tokens per session scan A 72b62470143a
spikard-developer is an agent published in the GitHub repository Goldziher/spikard (118 stars, last pushed 21d ago), licensed MIT. It adds 38 tokens to every session and 674 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 2026-08-30.
Other agents, from other repositories
gpui-researcher
Researches and validates GPUI usage patterns, APIs, and conventions. Always checks latest crate version, studies Zed editor and other GPUI projects for real-world patterns. Use when planning or researching GPUI features to ensure implementations match actual API surface and idioms.
research
Use this agent when the user asks an open-ended question about how the ast-index codebase works ("how is incremental update wired", "why don't we tree-sitter Perl", "what's the data flow for --format json", "which commands share scope filtering"). The agent reads the code, traces connections, and returns a structured…
rust-reviewer
You are a Rust code review agent for the ClaudeTerminal project - a Tauri 2.x desktop application.
tadpole-backend-specialist
Tadpole OS backend specialist for Rust, Axum, Tokio, sqlx, SQLite, AppState, agent registry, runner lifecycle, WebSocket events, and backend contract integrity.
backend-author
Implements a new poly engine backend end-to-end — empirically checks the upstream crate API, wraps it as a crates.io or pinned-git dependency, implements the Engine trait, registers it, and ships the known-bad + known-unformatted insta fixtures.
rust-build-fixer
Rust build, clippy, and rustfmt error resolution specialist for the GitCortex workspace. Use PROACTIVELY when cargo check/clippy/fmt fails. Produces minimal surgical fixes — no architectural changes, no API redesigns. Mirrors the Go build resolver pattern.