A comparative research command for evaluating a product, project, repository, or article against repositories known to Neotoma, a project knowledge system.

It detects the type of resource, researches it when needed, compares it with known repositories, creates analysis documents, and stores findings, tasks, and proposed issues.

It organizes competitive, partnership, or relevance research and records the resulting findings for later use.

analyze — Skill for Claude Code by markmhendrickson/ateles

Install

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.

Any agent

npx skills add markmhendrickson/ateles --skill analyze

Clone the repo

git clone --depth 1 https://github.com/markmhendrickson/ateles

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/markmhendrickson/ateles/analyze/github.svg)](https://agentmods.dev/skills/markmhendrickson/ateles/analyze)

Your own site

<a href="https://agentmods.dev/skills/markmhendrickson/ateles/analyze"><img src="https://agentmods.dev/badge/skills/markmhendrickson/ateles/analyze/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/markmhendrickson/ateles/analyze"><img src="https://agentmods.dev/badge/skills/markmhendrickson/ateles/analyze.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 91 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,974 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00091	$0.02974
Opus 5.5	$0.00036	$0.01190
Sonnet 5.5	$0.00018	$0.00595
Haiku 4.5	$0.00009	$0.00297

Measured 1mo ago against content hash c69d0aa8fc7f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

analyze 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 1mo 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.

.claude/skills/analyze/SKILL.md · 157 lines

How it starts

The opening of the file, as written. The whole thing — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Notes

This command is generic and works for any repo using foundation as submodule.
Comparative analysis: All analysis is relative to all repos. Load repos from Neotoma (repository entities). If empty, run execution/scripts/sync_repos_to_neotoma.py.
Output documents are confidential and stored in the private docs submodule. Persistence of findings to Neotoma (Step P below) is always performed; opening public issues (Step I) is opt-in.
Resource Type Detection: Command automatically detects if resource is a product/project (competitive/partnership analysis) or content/thought leadership (relevance analysis).
Templates ensure consistent, thorough analysis across all assessments.
For content/thought leadership, analysis focuses on extracting insights applicable to current repo rather than competitive positioning.
Web Scraper Integration: ChatGPT and Twitter/X URLs are automatically handled via web scraper MCP server when configured (see MCP configuration).
Browser Tools Fallback: Non-scraper URLs and search terms use browser tools for research.

Step P: Persist findings to Neotoma (required, same turn)

After producing the markdown analysis document (the existing foundation-template output), persist a structured record to Neotoma in the same turn per the Neotoma MCP turn lifecycle and [PROVENANCE] rules. This applies regardless of resource type (competitive, partnership, relevance) and regardless of whether public issues are also opened.

Entity-type reuse check (before first store in a fresh session)

Call list_entity_types with keywords analysis, task, issue, finding, repository to check for existing types. Reuse exact strings when present. Default types:

analysis — the overall analysis (one per invocation). Subtype the analysis kind via a kind field rather than minting separate top-level types.
task — Mark-internal follow-up actions extracted from the analysis.
proposed_github_issue — drafted public issues for repo-touching tasks (same type as used by /analyze-meeting).
analysis_finding — discrete findings inside the analysis (one entity per finding so they can be cross-referenced and aggregated independently). Reuse finding, insight, or similar if already present in the type registry.
repository — never created here; only retrieved via retrieve_entities for the comparative scope.

Read the full file on GitHub · 157 lines

Changes

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.

1mo ago First seen · 157 lines · 91 tokens per session scan A c69d0aa8fc7f

Subscribe to this mod's changes

analyze is a skill published in the GitHub repository markmhendrickson/ateles (5 stars, last pushed today), licensed MIT. It adds 91 tokens to every session and 2,974 once invoked, about $0.0004 per session on Opus 5.5. 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.

Analytics and metrics Autonomous Agents LLM Research aauth agent-swarm ai-agents claude

local-llm-tool

A local LLM execution tool. Requests text generation and chat from models on GPU via Ollama or vLLM. Use when: Use when: on-premise inference, calling Ollama endpoints, or needing summaries and generation with local models.

xuiltul/animaworks · 55 tokens

understand-codebase

Understand an unfamiliar codebase or plan a change safely, using Spine's deterministic knowledge-graph MCP tools. Reach for this before answering structural questions about a repo you don't know, before editing code, or when debugging — it hands you engineering decisions (what a change breaks, what's untested, where a…

synaptixs/spine · 226 tokens

analyze

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

Notes

Step P: Persist findings to Neotoma (required, same turn)

Entity-type reuse check (before first store in a fresh session)

What this file has done since we first saw it

Other skills, from other repositories

local-llm-tool

understand-codebase

continue

review-pr

tasks

roadmap