Skip to content
Agentmart
Submit a tool

code-ingest

Adds a code repository to the Obsidian code library with its purpose, usage, and links to research projects.

Skill by Vepricov

IndexedMIT★ 33
Write a review

Chalk Labs

Need help deploying code-ingest?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/vepricov-code-ingest

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Adds a code repository to the Obsidian code library with its purpose, usage, and links to research projects. Use when the user hands over a repo URL or path and says 'add to the code library', 'разбери репозиторий', or starts a project that uses a repo missing from Code/.

Use cases: research

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md and code. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/code-ingest

What's inside

Skill name
code-ingest
Description
Adds a code repository to the Obsidian code library with its purpose, usage, and links to research projects. Use when the user hands over a repo URL or path and says 'add to the code library', 'разбери репозиторий', or starts a project that uses a repo missing from Code/.
License
MIT
Instructions
103 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# code-ingest — add a repository to the Obsidian Code library

Turns a repo into a **map you can read in 2 minutes and instantly recall how the
code is organized and where to look to change something** — without duplicating
the source. The code itself stays in git / on the server; these notes are the index.

## When to use
- The user hands you a repo URL or path and says "add to the code library" / "разбери репо".
- A project starts depending on external code that has no `Code/<repo>/` folder yet.
- Before heavily editing an unfamiliar repo (build the map first).

## When NOT to use
- The repo is already in `Code/<repo>/` and unchanged → just read it. Re-run only to refresh after large upstream changes.
- For per-project edits/diffs → those go in the **project hub card** `## Код` section, not here (see [[code-library]]).

## Where it lives
Vault (the lab tree): `${OBSIDIAN_VAULT}/personal/code-library/`
One folder per repo: `personal/code-library/<repo-slug>/`. The slug is the repo name, kebab-case.

## Output structure (always)
```
Code/<repo>/
  <repo>.md          ← CANONICAL OVERVIEW. Always this exact name. Read this first.
  architecture.md    ← entrypoint, control/data flow, how a run executes end-to-end
  <module>.md        ← one note per major module/package (group tiny files)
  ...
```
- The overview `<repo>.md` is mandatory and always named after the folder, so any agent knows which file to open first.
- Split into module notes when the repo is large; for a tiny repo a single `<repo>.md` is fine.
- Update `Code/README.md` (the library index) with a one-line entry for the new repo.

## Procedure
1. **Get the source.** Prefer reading a local clone or the server copy if one exists (ask / check the project card). Otherwise fetch file listing + key files from GitHub (raw URLs / `gh`). Note the canonical git URL and default branch.
2. **Map the layout.** List top-level dirs and the role of each. Identify: entrypoint(s), config system, the main loop, the factory/registry or dispatch points (where names map to classes), data path, outputs/checkpoints.
3. **Trace one full run** end-to-end (what `main` does, in order) — this becomes `architecture.md`.
4. **Write module notes** using the template below. For each module: what it's for, key files with **GitHub permalinks and line anchors**, key classes/functions, and an explicit **"where to edit to change X"** list. Do not paste code bodies — cite `path:line` + a one-line description.
5. **Write the overview `<repo>.md`** using its template.
6. **Index it** in `Code/README.md`.
7. Tell the user what was created and link the overview.

## Overview template (`<repo>.md`)
```markdown
---
tags: [code, <repo-slug>]
repo: <git url>
default_branch: <branch>
created: DD-MM-YYYY
---
# <repo> — code map

One-paragraph: what this repo is and what you use it for.

## At a glance
- **Entrypoint:** `path` (`func`)
- **Config:** how runs are parametrized (flags / yaml / hydra)
- **Run a job:** the minimal command
- **Data:** where data lives / how it's loaded
- **Outputs:** where checkpoints / logs / metrics go
- **Dispatch points:** where a name (optimizer/model/dataset) maps to a class

## Directory map
| path | role | note |
|------|------|------|
| ... | ... | [[architecture]] / [[<module>]] |

## Where to look to change X
- change the model arch → [[models]] (`...`)
- add an optimizer → [[optimizers]] (`...`)
- change the schedule → ...
- change data → ...

## Notes
- [[architecture]] · [[optimizers]] · [[models]] · [[data]] · ...

## Used by projects
- [[<направление>/<тема>/<работа>/README|<работа>]] — <fork/branch + what's changed>
```

## Module note template (`<module>.md`)
```markdown
# <module>

What this module is responsible for, in 2-3 sentences.

## Key files
- `path/to/file.py` — role. [GitHub](permalink)
  - `ClassOrFunc` (`file.py:LINE`) — what it does.

## How it fits the run
Where this is called from (link [[architecture]]), inputs/outputs.

## Where to edit to change X
- ... → `file.py:LINE`
```

## Rules
- **Never copy large code blocks.** Cite `path:line` + GitHub permalink + a sentence. The notes are a map, not a mirror.
- Keep each note focused; 200-400 lines max, split if larger.
- Pin permalinks to the analyzed commit/branch so line anchors stay valid; note the branch.
- Use Obsidian wikilinks between the overview and module notes.
- After ingesting, remind the user to add a `## Код` section to the relevant project hub card (see [[code-library]]).

From Vepricov/claude-brainlab, MIT.

More from Vepricov/claude-brainlab

Signals

Stars
33
Forks
5
Open issues
1
Last commit (this folder)
Oct 19, 2026 (11 days ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from Vepricov

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get code-ingest running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying code-ingest?

CallGet help
Cite this page

code-ingest skill. Agent Mart. https://agentmart.dev/skills/vepricov-code-ingest (last updated 2026-10-24)