readmenator-ask SKILL.md skillA

readmenator-ask from grisuno/lazyown is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add grisuno/lazyown/readmenator-ask@git:20261008.72e5054

Pins git:20261008.72e5054 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
grisuno/lazyown
Path
.claude/skills/readmenator-ask/SKILL.md
Versions recorded
1
Latest version
git:20261008.72e5054, committed Oct 8, 2026
Size
2,446 bytes
Repository stars
300
License
AGPL-3.0

Answer questions about a ReadMenator-indexed codebase with GraphRAG retrieval (BM25 + Personalized PageRank over files, symbols, concepts, and source excerpts; map-reduce over community reports). Use for "where/how/why does X", "what handles Y", "what are the main subsystems or risks", before opening source files.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# ReadMenator: ask the graph

The GraphRAG index in `readmenator-graphrag/` was built offline from the static scan (zero LLM
tokens). Querying it returns a compact, cited Markdown context; you spend tokens only on reading
the answer.

## Commands

```bash
readmenator . ask "how are communities detected"            # auto: local or global
readmenator . ask "PersonalizedPageRank seeds" --local      # entity-centric
readmenator . ask "main subsystems and risks" --global      # corpus-wide, from community reports
readmenator . ask "taint propagation" --budget 1500         # cap the context (tokens)
readmenator . graphrag                                      # rebuild only the index
```

MCP: `readmenator.graphrag {"query": "...", "mode": "auto|local|global", "budget_tokens": 0}`;
resource `readmenator://graphrag` returns all community reports.

## Which mode

- **local** (specific names, behaviours, "where is", "how does X work"): BM25 finds matching
  entities and source chunks, Personalized PageRank spreads relevance through imports, calls,
  inheritance and definitions, and you get Entities (with `file:line`), Relationships,
  Community reports, and Sources (real code excerpts).
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add grisuno/lazyown/readmenator-ask@sha256:237b06ada9a9d379

The line at the top of this page pins the label git:20261008.72e5054, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_qrqhxyjs7iadwrx5.svg)](https://markdownregistry.com/a/art_qrqhxyjs7iadwrx5)

4 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 1 version of this file, committed on Oct 8, 2026.

versioncommittedcommitsizeaudit
git:20261008.72e5054 latest2026-10-08 72e5054 2,446 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (2446 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

grisuno/lazyown · 300 stars · license AGPL-3.0 · pushed 2026-11-01 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_qrqhxyjs7iadwrx5
GET https://markdownregistry.com/api/v1/resolve?ref=grisuno/lazyown/readmenator-ask
GET https://markdownregistry.com/api/v1/blob/237b06ada9a9d3797d9a9e2774b8d686d6eea2f70dfdf748be74cabad3dfa9fe

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from grisuno/lazyown

readmenator-change SKILL.md skill
grisuno/lazyown · .claude/skills/readmenator-change/SKILL.md · Safe-change protocol for ReadMenator-indexed repositories. Use before editing, refactoring, deleting, or adding code…
git:20261008.72e5054 · audit A · 300 stars
readmenator-memory SKILL.md skill
grisuno/lazyown · .claude/skills/readmenator-memory/SKILL.md · Persist and recall cross-session project knowledge (business rules, decisions and their reasons, workflow, constraints…
git:20261008.72e5054 · audit A · 300 stars
readmenator-orient SKILL.md skill
grisuno/lazyown · .claude/skills/readmenator-orient/SKILL.md · Start-of-session orientation for any repository that has ReadMenator outputs (readmenator-agent/, readmenator-wiki/…
git:20261022.f2f4471 · audit A · 300 stars
readmenator-receipts SKILL.md skill
grisuno/lazyown · .claude/skills/readmenator-receipts/SKILL.md · Ingest deploynator release receipts into the repository knowledge base and turn observed release evidence into graph…
git:20261022.f2f4471 · audit A · 300 stars
run-lazyown SKILL.md skill
grisuno/lazyown · .claude/skills/run-lazyown/SKILL.md · Build, launch, and drive the LazyOwn red-team framework (the cmd2 shell in lazyown.py). Use when asked to run, start…
git:20261007.c43c781 · audit A · 300 stars
AGENTS.md AGENTS.md file
grisuno/lazyown · AGENTS.md
git:20261030.230476b · audit A · 300 stars
CLAUDE.md CLAUDE.md file
grisuno/lazyown · CLAUDE.md
git:20261030.230476b · audit A · 300 stars
llms.txt@readmenator-maps llms.txt file
grisuno/lazyown · readmenator-maps/llms.txt
git:20261031.1c4f270 · audit A · 300 stars
adversary-yaml-creator SKILL.md skill
grisuno/lazyown · skills/adversary-yaml-creator/SKILL.md · Create LazyOwn adversary YAMLs in one shot: APT playbooks (playbooks/apt_*.yaml), orchestration chains (chains/*.yaml)…
git:20261031.1c4f270 · audit A · 300 stars
apt-emulation SKILL.md skill
grisuno/lazyown · skills/apt-emulation/SKILL.md · Emulate APT adversaries end-to-end in LazyOwn: research MITRE ATT&CK techniques, translate them to Atomic Red Team…
git:20261016.87c0ac4 · audit A · 300 stars
atomic-exploit SKILL.md skill
grisuno/lazyown · skills/atomic-exploit/SKILL.md · Extend the autonomous loop's arsenal without touching Python: add one exploits/<id>.yaml per exploit (service triggers…
git:20261016.87c0ac4 · audit A · 300 stars
awesome-windows-security SKILL.md skill
grisuno/lazyown · skills/awesome-windows-security/SKILL.md · Route a Windows offensive objective to the right tool and run it inside LazyOwn. Uses chryzsh/awesome-windows-security…
git:20261021.9f1ab88 · audit B · 300 stars

Every file in grisuno/lazyown

Browse by kind, by grade A, or by owner.