architecture-reading SKILL.md skillC
architecture-reading from atnexuslab/tightship is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add atnexuslab/tightship/architecture-reading@git:20261015.8e86e2cPins git:20261015.8e86e2c in mdr.lock. Pin the fingerprint instead.
- Audit grade
- C, 14 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- atnexuslab/tightship
- Path
content/skills/architecture-reading/SKILL.md- Versions recorded
- 1
- Latest version
- git:20261015.8e86e2c, committed Oct 15, 2026
- Size
- 11,208 bytes
- Repository stars
- 4
- License
- MIT
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
+++
name = "architecture-reading"
description = "Use before a non-trivial change in an unfamiliar or large codebase — read it ground → data → backend → frontend → seam, then say where the change belongs and what constrains it."
+++
# Architecture Reading
## When to use
- Before planning a feature, refactor, or bugfix in code you don't already understand.
- When a change crosses a module, layer, or app boundary.
- When reality is suspected to diverge from the repo's documented architecture.
- To produce the map the `arch` axis of `{{command:audit}}` returns.
## Scope the read to the change
Depth is set by the change, not by the size of the repo. A change confined to one layer reads that layer
deeply and the neighbours only where they touch it; a change that crosses layers reads every pass it
crosses, end to end. Mapping a codebase completely is a documentation project — this is not that.
Skip any pass the repo doesn't have (no database, no frontend) and say you skipped it.
## Why this order
Read **ground → data → back → front**, then close the seam.
Each layer is constrained by the one before it. Data outlives the code that reads it: the schema records
…Read the whole file at its exact version.
How to install
mdr add atnexuslab/tightship/architecture-reading@sha256:65e8ba653ba60f1cThe line at the top of this page pins the label git:20261015.8e86e2c, 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.
[](https://markdownregistry.com/a/art_lw465t5dj7shwhuc)
2 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 1 version of this file, committed on Oct 15, 2026.
Audit of the latest version
- fail: Frontmatter block present
- fail: Frontmatter declares a name
- fail: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (11208 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
Starting a new one? Use a template for SKILL.md on mdpantry, which passes every one of these checks and says what to change in it.
Source
atnexuslab/tightship · 4 stars · license MIT · pushed 2026-10-22 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_lw465t5dj7shwhuc GET https://markdownregistry.com/api/v1/resolve?ref=atnexuslab/tightship/architecture-reading GET https://markdownregistry.com/api/v1/blob/65e8ba653ba60f1cb34dd1306b519886a3bef6d89e860f68893dcf439f98b324
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.