agentmods.dev

polywise: Skill for Codex

.codex/skills/agentmap-generator/SKILL.md

agentmap-generator is a skill for Codex from MatrixAges/polywise. It costs 48 tokens per session (302 once invoked), scanned A, original, MIT.

A guide for maintaining package-level agentmap.md files, which are short maps of a code package's folders and responsibilities. It says how to inspect the real file tree and keep the map concise and accurate.

In plain words
What is it for?
Use it when reorganising a package or changing its responsibilities to update the folder map and its summary from the actual files on disk.
Why use it?
It keeps structural documentation aligned with the codebase when folders or ownership boundaries change, without documenting every small file.

Skill for Codex

Written for Codex: installed under .codex/.

This is MatrixAges/polywise's own configuration. It tells Codex how to work on polywise itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything polywise configures →

not rated 654repo +5 4mo ago A scan SkillSpector: pass 48 tokens original MIT
View source ↗ MatrixAges/polywise polywise.io
Reuse

Borrowing it

Nothing to install: this file belongs to MatrixAges/polywise. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/MatrixAges/polywise/master/.codex/skills/agentmap-generator/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/MatrixAges/polywise

Made for: Codex.

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 agentmap-generator

README.md
[![agentmods](https://agentmods.dev/badge/skills/matrixages/polywise/agentmap-generator/github.svg)](https://agentmods.dev/skills/matrixages/polywise/agentmap-generator)
Your own site
<a href="https://agentmods.dev/skills/matrixages/polywise/agentmap-generator"><img src="https://agentmods.dev/badge/skills/matrixages/polywise/agentmap-generator/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 agentmap-generator

Your own site · 80×15
<a href="https://agentmods.dev/skills/matrixages/polywise/agentmap-generator"><img src="https://agentmods.dev/badge/skills/matrixages/polywise/agentmap-generator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 48 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 302 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00048 $0.00302
Opus 5.5 $0.00019 $0.00121
Sonnet 5.5 $0.00010 $0.00060
Haiku 4.5 $0.00005 $0.00030

Measured 2mo ago against content hash 1ac834944b7d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

agentmap-generator 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 2mo 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.

.codex/skills/agentmap-generator/SKILL.md · 36 lines

What it actually says

Agentmap Generator

Update the package's agentmap.md whenever package structure or core responsibility boundaries change.

Keep the map faithful to disk:

  • Re-scan the actual package tree before editing the map.
  • Do not invent files, folders, or responsibilities.
  • Exclude transient or protected folders such as names starting with __.

Keep the map at outline level:

  • Prefer top-level folders and major business subdomains.
  • Stop at 1-2 levels deep in most packages.
  • Use a third level only for large, stable coordination roots such as runtime kernels or data layers.
  • Do not enumerate routine leaf files, repeated component atoms, or generated outputs.

Keep descriptions short:

  • Describe folders by responsibility, not implementation detail.
  • Mention files only when they are entry points, public coordinators, or important infrastructure roots.
  • Prefer a few stable ownership statements over exhaustive file-by-file noise.

Keep the structure stable:

  • Use a fenced json block for the tree.
  • Preserve existing top-level sections when they are still valid.
  • Update both the tree and the prose summary when responsibilities changed.

Before finishing, verify that every changed package with an agentmap.md still matches the current outline on disk.

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. 2mo ago First seen · 36 lines · 48 tokens per session scan A 1ac834944b7d

Subscribe to this mod's changes

agentmap-generator is a skill published in the GitHub repository MatrixAges/polywise (654 stars, last pushed 4mo ago), licensed MIT. It adds 48 tokens to every session and 302 once invoked, about $0.0002 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 2026-09-04.

Building agentsWriting and docsagentagentic-aiagentic-content-systemaiassistantcontent-system
Related

agentmap-generator compared with skills from other repositories

agentmap-generator next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
agentmap-generatorMatrixAges/polywiseSkill6544mo agoMITA48Codex
writing-workflow-skillsJetBrains/thinkrailSkill7.8kyesterdayApache-2.0A60Claude Code, Codex
artifact-deploykirodotdev/KiroCrewSkill4.8kyesterdayApache-2.0A74Claude Code, Codex
explain-forkirodotdev/KiroCrewSkill4.8kyesterdayApache-2.0A71Claude Code, Codex
writing-specsJetBrains/thinkrailSkill7.8kyesterdayApache-2.0A59Claude Code, Codex
mochi-remindkirodotdev/KiroCrewSkill4.8kyesterdayApache-2.0A20Claude Code, Codex
papyrus-latex-suggestionskirodotdev/KiroCrewSkill4.8kyesterdayApache-2.0A69Claude Code, Codex