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 skills add spedas/spedas_agent_kit --skill spedas-agent-kit-anatomygit clone --depth 1 https://github.com/spedas/spedas_agent_kitWrote 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/spedas/spedas_agent_kit/spedas-agent-kit-anatomy)<a href="https://agentmods.dev/skills/spedas/spedas_agent_kit/spedas-agent-kit-anatomy"><img src="https://agentmods.dev/badge/skills/spedas/spedas_agent_kit/spedas-agent-kit-anatomy/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/spedas/spedas_agent_kit/spedas-agent-kit-anatomy"><img src="https://agentmods.dev/badge/skills/spedas/spedas_agent_kit/spedas-agent-kit-anatomy.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00287 | $0.01315 |
| Opus 5 | $0.00143 | $0.00658 |
| Sonnet 5 | $0.00057 | $0.00263 |
| Haiku 4.5 | $0.00029 | $0.00131 |
Grade A, and why
spedas-agent-kit-anatomy 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 10d 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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
spedas_agent_kit anatomy — the convention & maintenance contract
The spedas_agent_kit repo is mapped by a tree of ANATOMY.md files (root + src/spedas_agent_kit/, analysis/, datasources/). This skill is the convention; those files are the content. It is the top-level maintenance guide for any coding agent touching this repo.
What an ANATOMY.md is
A code-cited structural map of one folder, written for an agent reader, next to the code. Every structural claim points at a file:line. It is NOT a manual (those are the analysis skills), an API contract (tool schemas), or rationale (commit messages / PRs). If a claim can't cite a line, it doesn't belong in anatomy.
A folder earns an ANATOMY.md when an agent could usefully reason about it as a unit without first reading siblings. Trivial leaves don't. The repo-root anatomy is the only file with a complete child enumeration.
The 6-section template (~80-line cap)
- What this is — one paragraph naming the concept the folder embodies.
- Components — files/functions/types with
file:linecitations + one-line purposes. - Connections — what calls in, what it calls out, what data flows through.
- Composition — parent + subfolders (each linked to its own
ANATOMY.md). - State — persistent state written; ephemeral state managed.
- Notes — bounded rationale/gotchas not visible in code.
Citations look like src/spedas_agent_kit/server.py:1072. Keep them current — they drift when code moves; fixing drift is part of any edit.
Maintenance contract (do these in the SAME commit as the code change)
- Add/rename/move a tool → update
src/spedas_agent_kit/ANATOMY.md(and root if the surface count changes). New capability lands as a unifiedsource_typeor a skill, NOT a new top-level tool, unless it truly cannot be either (the consolidation goal: keep the advertised base surface small; verify the current count withscripts/smoke_mcp_list_tools.py). - Add an analysis function → put it in
analysis/, register it increate_server(), add its backend to_ANALYSIS_REQUIRED_IMPORTSat the submodule path (server.py:55; a package-level probe silently hides ALL analysis tools), and updateanalysis/ANATOMY.md. - Add a data source →
datasources/with a preciserequire_*guard; updatedatasources/ANATOMY.md. - Add a skill → create or edit the canonical dir under
src/spedas_agent_kit/resources/skills/, follow the existing SKILL.md shape (When to use / Tool chain / Backend with VERIFIED contract / Procedure / Guardrails / Example), index it inspedas-skills-index, reference only the unified tools, then refresh runtime fixtures withscripts/export_packaged_skills.py --target <wrapper>/skills --clean.
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.
- 10d ago First seen · 69 lines · 287 tokens per session scan A 7397283368c2
spedas-agent-kit-anatomy is a skill published in the GitHub repository spedas/spedas_agent_kit (3 stars, last pushed 1mo ago), licensed MIT. It adds 287 tokens to every session and 1,315 once invoked, about $0.0014 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…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…