analyze-neotoma-feedback

analyze-neotoma-feedback is a skill for Claude Code from markmhendrickson/ateles. It costs 131 tokens per session (9,892 once invoked), scanned A, original, MIT.

A customer-development analysis tool for studying feedback about Neotoma, a product or project, from individual sources or across a collection of feedback.

In plain words
What is it for?
It analyzes URLs, files, or pasted feedback; compares themes across sources; and suggests actions, content ideas, market insights, and messaging ideas.
Why use it?
It turns scattered feedback into evidence about customer needs, positioning, product effectiveness, target users, language, and adoption barriers.

Skill for Claude Code

Written for Claude Code: user-invocable in frontmatter. Also seen: mentions Codex; built for openclaw.

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /Users/markmhendrickson/repos/neotoma/docs/icp/primary_icp.md.

Good fit It analyzes URLs, files, or pasted feedback; compares themes across sources; and suggests actions, content ideas, market insights, and messaging ideas.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

There is no command for this one: it runs only inside a plugin, and the catalogue could not identify which plugin ships it. The source is linked below.

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.

agentmods badge for analyze-neotoma-feedback

README.md
[![agentmods](https://agentmods.dev/badge/skills/markmhendrickson/ateles/analyze-neotoma-feedback/github.svg)](https://agentmods.dev/skills/markmhendrickson/ateles/analyze-neotoma-feedback)
Your own site
<a href="https://agentmods.dev/skills/markmhendrickson/ateles/analyze-neotoma-feedback"><img src="https://agentmods.dev/badge/skills/markmhendrickson/ateles/analyze-neotoma-feedback/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.

agentmods 80×15 button for analyze-neotoma-feedback

Your own site · 80×15
<a href="https://agentmods.dev/skills/markmhendrickson/ateles/analyze-neotoma-feedback"><img src="https://agentmods.dev/badge/skills/markmhendrickson/ateles/analyze-neotoma-feedback.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 131 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 9,892 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00131 $0.09892
Opus 5 $0.00066 $0.04946
Sonnet 5 $0.00026 $0.01978
Haiku 4.5 $0.00013 $0.00989

Measured 9d ago against content hash b5a49340c474, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

analyze-neotoma-feedback 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 9d 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-neotoma-feedback/SKILL.md · 570 lines

How it starts

The opening of the file, as written. The whole thing — 570 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Analyze Neotoma Feedback

Produce axis-by-axis customer-development analysis grounded in Neotoma's canonical ICP and positioning.

Two modes:

  • Per-item mode (default): one source in, one report + one feedback_analysis entity out.
  • Aggregate mode: the entire corpus of feedback-type entities in Neotoma in, one cross-item synthesis report + one feedback_aggregate_analysis entity out. See Aggregate Mode below.

This skill complements process-feedback:

  • process-feedback = triage and release-stage assessment (bucket, action, evidence threshold).
  • analyze-neotoma-feedback = deep customer-development analysis (per-item or aggregate).

Run triage first when useful; this skill then goes deeper on items worth deeper analysis.

Invocation

/analyze-neotoma-feedback <source>                # per-item
/analyze-neotoma-feedback --aggregate [--since YYYY-MM-DD] [--types t1,t2,...]

For per-item, <source> is auto-detected:

  • URL (starts with http:// or https://) — delegate to user-web-scraper MCP as in the analyze skill. Handles ChatGPT share, x.com/twitter, blog posts.
  • Absolute file path (exists on disk) — read the file. Handles meeting transcripts (e.g. .cursor/last_meeting_transcription.txt), email attachments, images, screenshots.
  • Neotoma entity reference — a UUID or a short identifier string (person name, email, conversation title). Resolve via retrieve_entity_by_identifier first, then retrieve_entities scoped to entity_type in {product_feedback, agent_message, note, conversation, email_message}.
  • Raw pasted text — anything that doesn't match the above.
  • --aggregate flag (with no positional source) — switches to aggregate mode.

If the resolution is ambiguous (e.g. the string matches multiple entities), list the top 3 candidates and ask the user to pick one.

Step 1: Load canonical context

Read once per invocation, cite in the report where referenced. Skip any missing file with a [gap: <path>] note instead of failing.

Read the full file on GitHub · 570 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.

  1. 9d ago First seen · 570 lines · 131 tokens per session scan A b5a49340c474

Subscribe to this mod's changes

analyze-neotoma-feedback is a skill published in the GitHub repository markmhendrickson/ateles (6 stars, last pushed yesterday), licensed MIT. It adds 131 tokens to every session and 9,892 once invoked, about $0.0007 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.