agentsclimarketplace
Sign in

Repo orient

Skill contextosai/skills/skills/repo-orient

Map an unfamiliar software repository from code and configuration. Use when Codex needs to understand a new codebase, locate entry points or ownership boundaries, explain architecture and runtime flow, identify where a change belongs, or prepare for implementation without yet modifying files. Produce an evidence-backed repository map, not a directory listing or README paraphrase.From its SKILL.md

Install
npx -y skills add contextosai/skills --skill repo-orient

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

  • 1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
  • runs commandsInstructs the agent to run 2 commands, including `git status` and 1 more.

SKILL.md

2.3 KB, 399 tokens by cl100k_base, as published. Nobody here has run it

Repository Orientation

Build the smallest accurate mental model needed for the user's task.

Protocol

  1. Read applicable AGENTS.md files and inspect git status. Treat existing changes as user work.
  2. Inventory with rg --files, bounded by relevant top-level directories. Identify manifests, lockfiles, build/test config, deployment config, and generated/vendor boundaries.
  3. Infer the repository shape: application, library, monorepo, service set, plugin, infrastructure, or hybrid. Verify the inference from manifests.
  4. Trace one real execution path from an external entry point to its terminal effect. Follow imports/calls, configuration, persistence, and outbound I/O; do not infer architecture from names alone.
  5. Trace the requested concern separately. Locate its definition, runtime wiring, tests, and operational surface. Search symbols and call sites before reading entire large files.
  6. Identify boundaries that constrain a change: public API, data/schema, process/service, trust/authorization, transaction, concurrency, and release.
  7. Stop when the model answers the user's question. Do not exhaustively catalog unrelated modules.

Evidence discipline

  • Cite concrete path:line references for important claims.
  • Distinguish observed facts from inferences. State what would falsify an inference when uncertainty matters.
  • Treat README and diagrams as orientation leads, then reconcile them with executable code and configuration.
  • Call out stale, duplicated, dead, generated, or bypassed paths.
  • If multiple entry points differ materially, map each relevant path rather than inventing one universal flow.

Output

Use references/repository-map.md. Lead with the answer the user needs, then give the execution path, boundaries, change location, and open questions. Skip sections that add no decision value.

Do not edit the repository unless the user also requests a change.

What ships with it: 2 files

1.4 KB alongside SKILL.md

agents/

references/

Gives 0 of the 12 instructions most architecture codebase skills give in 399 tokens

Counted across 858 of the 1,304 authors here whose files we hold, read 2026-09-06

  • Apply the deletion test to identify shallow modulesin 32 of 858, across 31 files
  • Read domain glossary and ADRs before exploringin 22 of 858, across 19 files
  • Use Tailwind and Mermaid via CDN for reportsin 21 of 858, across 18 files
  • Document architecture decision recordsin 20 of 858, across 12 files
  • Offer to record ADRs for rejected candidatesin 17 of 858, across 14 files
  • Limit primary navigation to four to seven itemsin 17 of 858, across 7 files
  • Write HTML report to the system temp directoryin 17 of 858, across 14 files
  • Read product marketing context before asking questionsin 16 of 858, across 6 files
  • Use Mermaid graph TD for visual sitemapsin 15 of 858, across 5 files
  • Ensure every page has at least one internal linkin 15 of 858, across 5 files
  • Use ASCII tree format for page hierarchy draftsin 15 of 858, across 5 files
  • Enforce lowercase URLs with hyphensin 15 of 858, across 5 files

Said here and by no other author read

  • Read AGENTS.md and inspect git status
  • Inventory files using rg
  • Infer repository shape from manifests
  • Trace one real execution path
  • Trace the requested concern separately
  • Search symbols and call sites

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

Keep looking

Skills are one crate of 325,949. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.