Agent skill

Deply Config

by Vashkatsi in Vashkatsi/deply

A skill your agent uses when creating, auditing, validating, or integrating Deply v1.2.1 architecture configuration files for Python projects, including deply.yaml, light/medium/strict guidance…

MITAuto-check passedDevelopment

Install Deply Config

skills CLI
$ npx skills add Vashkatsi/deply --skill deply-config -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install Vashkatsi/deply deply-config --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/Vashkatsi/deply.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/deply-config .claude/skills/deply-config && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
deply-config
GitHub stars
173
Token cost
~945 tokens
SKILL.md length
417 words
Files
11 (incl. references)
Skills in repo
1
Repo updated
First seen
Licence
MIT

At a glance

A skill your agent uses when creating, auditing, validating, or integrating Deply v1.2.1 architecture configuration files for Python projects, including deply.yaml, light/medium/strict guidance…

  • Works in 9 steps: Inspect the repository before asking… → Ask only for intent that cannot be… → Read the needed references → …
  • Integrating Deply v1.2.1 architecture configuration files for Python projects
  • SKILL.md covers Workflow, Rules and Final Output Contract
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Deply Config is an agent skill from Vashkatsi/deply. Use when creating, auditing, validating, or integrating Deply v1.2.1 architecture configuration files for Python projects, including deply.yaml, light/medium/strict guidance, monorepos, CI, Makefiles, and architecture documentation.

Its SKILL.md is about 950 tokens, which your agent loads only when the skill is triggered. The skill folder holds 12 other files, including reference files (for example `agents/openai.yaml`, `references/adoption-and-audit.md` and `references/architecture-recipes.md`).

It sits in Development, covering Monorepo tooling. It works with Python. The repository describes itself as: Keep your python architecture clean. The licence is MIT.

When your agent uses it

  • Integrating Deply v1.2.1 architecture configuration files for Python projects
  • Including deply.yaml
  • Light/medium/strict guidance
  • Architecture documentation

Example prompts

  • “/deply-config”

Requirements

  • Python 3

Workflow steps

9 steps, taken from the first numbered list in SKILL.md.

  1. Inspect the repository before asking questions
  2. Ask only for intent that cannot be discovered
  3. Read the needed references
  4. Choose the mode
  5. Run deply validate --config=deply.yaml from the project root.
  6. Run deply analyze --parallel --config=deply.yaml from the project root.
  7. If violations exist, triage them before editing. Fix collectors/excludes first. Only use --max-violations=N when the user chooses…
  8. Add local command, CI step, and short architecture docs when requested.
  9. Finish with the output contract below.

What it can do on your machine

Read from SKILL.md and the folder at commit 0556b51. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Deply Config loads about 945 tokens when it runs, and up to ~7.4k if it reads all its reference files. Until then it costs about 61 tokens; SKILL.md has 417 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~61
When it runs · the whole SKILL.md, loaded when a task matches
~945
With references · SKILL.md plus every file in references/, read only if the agent opens them
~7.4k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from Vashkatsi/deply at commit 0556b51, republished under its MIT licence (© Vashkatsi). 417 words, ~945 tokens.

Download SKILL.mdSave it as .claude/skills/deply-config/SKILL.md (or your agent's skills folder). This skill also uses 10 other files; get the full folder from GitHub.
name
deply-config
description
Use when creating, auditing, validating, or integrating Deply v1.2.1 architecture configuration files for Python projects, including deply.yaml, light/medium/strict guidance, monorepos, CI, Makefiles, and architecture documentation.
license
MIT
metadata.version
1.2.1

Deply Config

Use this skill to create or audit a production-ready deply.yaml for a Python project and wire it into local checks, CI, and documentation.

Workflow

  1. Inspect the repository before asking questions:
    • Package tree and Python source roots.
    • pyproject.toml, setup.py, setup.cfg, requirements files, lockfiles.
    • Makefile, .github/workflows/, .gitlab-ci.yml, tox/nox/pre-commit config.
    • Existing docs, architecture notes, and framework imports.
    • Existing deply.yaml files and deply:ignore / deply:ignore-file suppressions.
  2. Ask only for intent that cannot be discovered:
    • Preserve current architecture or enforce a target architecture.
    • Strictness: light, medium, or strict.
    • CI rollout: fail immediately or adopt with a temporary --max-violations=N ratchet.
  3. Read the needed references:
    • references/discovery.md first for deterministic repository inspection before asking questions.
    • references/deply-v1-schema.md for exact Deply v1.2.1 YAML, collectors, rules, and validation constraints.
    • references/architecture-recipes.md when choosing a target architecture style.
    • references/presets.md for light, medium, and strict Agent Skill profiles.
    • references/framework-presets.md for Agent Skill guidance when the repo uses Django, FastAPI, Flask, Celery, or SQLAlchemy.
    • references/adoption-and-audit.md when auditing an existing config or adopting Deply in a legacy project.
    • references/monorepo.md when the repo has multiple apps, packages, or services.
    • references/violation-triage.md when deply analyze reports violations.
    • references/ci-and-docs.md when adding Makefile, CI, or documentation changes.
  4. Choose the mode:
    • Create/update mode: generate or improve deply.yaml with public root key deply:.
    • Audit mode: review existing config, CI, docs, and suppressions before proposing changes.
  5. Run deply validate --config=deply.yaml from the project root.
  6. Run deply analyze --parallel --config=deply.yaml from the project root.
  7. If violations exist, triage them before editing. Fix collectors/excludes first. Only use --max-violations=N when the user chooses non-blocking adoption.
  8. Add local command, CI step, and short architecture docs when requested.
  9. Finish with the output contract below.
Show full SKILL.md (142 more words)Show less

Rules

  • Prefer the smallest config that enforces the intended boundaries.
  • Do not invent unsupported keys such as allow_layer_dependencies.
  • Do not add generated files, tests, migrations, virtualenvs, build output, or vendored code to analysis scope.
  • Keep domain/business layers independent from frameworks, persistence, transport, and SDKs when using medium or strict.
  • Do not add new Deply suppressions unless the user accepts a specific architectural reason.
  • Report existing suppressions separately from new violations.
  • Validate every config with the installed Deply CLI before presenting it as complete.

Final Output Contract

End every run with:

  • Changed files.
  • Mode: create/update or audit.
  • Strictness: light, medium, strict, or not changed.
  • Validation command and result.
  • Analyze command and result.
  • Current violation count.
  • Existing suppression count and any new suppressions added.
  • CI behavior: blocking, non-blocking, ratchet with exact --max-violations=N, or not changed.
  • Follow-up work, only if required to finish adoption safely.

© Vashkatsi, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 10 other files (references) in skills/deply-config of Vashkatsi/deply.

  • SKILL.md
  • agents/openai.yaml
  • references/adoption-and-audit.md
  • references/architecture-recipes.md
  • references/ci-and-docs.md
  • references/deply-v1-schema.md
  • references/discovery.md
  • references/framework-presets.md
  • references/monorepo.md
  • references/presets.md
  • references/violation-triage.md

Open the folder on GitHubat commit 0556b51

Compare with similar skills

Deply Config next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Deply Config compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Deply Config this skillVashkatsi/deply173—~945Automated safety check: PassMIT
Tbdjlevy/strif131—~3.5kAutomated safety check: PassMIT
Light Project StructureLight0305/Light-skills640—~3kAutomated safety check: NotesMIT
Metaxyanam-org/metaxy124—~1.5kAutomated safety check: PassApache-2.0
Claude Settings Auditgetsentry/skills1k4 repos~3kAutomated safety check: PassApache-2.0
Rocky Devrocky-data/rocky304—~2.1kAutomated safety check: PassApache-2.0

Similar skills

  • Tbd

    jlevy/strif

    Git-native issue tracking (beads), coding guidelines, knowledge injection, and spec-driven planning for AI agents.

    131 GitHub stars~3.5k tokensUpdated 4 mo ago
    DevelopmentAuto-check passed
  • Light Project Structure

    Light0305/Light-skills

    Audits, scaffolds and safely migrates research project folder structures, keeping existing repositories read-only until you approve exact moves from a plan.

    640 GitHub stars~3k tokensUpdated 3 mo ago
    DevelopmentAuto-check: notes
  • Metaxy

    anam-org/metaxy

    This skill should be used when the user asks to "define a feature", "create a BaseFeature class", "track feature versions", "set up metadata store", "field-level lineage", "FieldSpec", "FeatureDep"…

    124 GitHub stars~1.5k tokensUpdated 10 days ago
    DevelopmentAuto-check passed
  • Claude Settings Audit

    getsentry/skills

    Official

    Analyze a repository to generate recommended Claude Code settings.json permissions.

    1k GitHub starsUsed in 4 repos~3k tokens
    DevelopmentAuto-check passed
  • Rocky Dev

    rocky-data/rocky

    Top-level router for Rocky development tasks. An agent skill from rocky-data/rocky.

    304 GitHub stars~2.1k tokensUpdated yesterday
    DevelopmentAuto-check passed
  • Scaffold Project

    Marve10s/Better-Fullstack

    Scaffold a new app, API, backend, fullstack project, mobile app, polyglot service, monorepo, or starter with Better Fullstack.

    756 GitHub stars~716 tokensUpdated today
    DevelopmentAuto-check passed

Works with

Categories

Questions about Deply Config

What does Deply Config do?

A skill your agent uses when creating, auditing, validating, or integrating Deply v1.2.1 architecture configuration files for Python projects, including deply.yaml, light/medium/strict guidance…. Deply Config is an agent skill from Vashkatsi/deply.yaml, light/medium/strict guidance, monorepos, CI, Makefiles, and architecture documentation.

When should I use Deply Config?

Deply Config fits situations like: integrating Deply v1.2.1 architecture configuration files for Python projects; including deply.yaml; light/medium/strict guidance; architecture documentation.

How do I install Deply Config in Claude Code?

Run `npx skills add Vashkatsi/deply --skill deply-config -a claude-code`. Or copy the skill folder (skills/deply-config in Vashkatsi/deply) into .claude/skills/deply-config in your project. Claude Code loads it when a task matches its description.

How do I install Deply Config in Codex?

Run `npx skills add Vashkatsi/deply --skill deply-config -a codex`. Or copy the skill folder (skills/deply-config in Vashkatsi/deply) into .agents/skills/deply-config in your project. Codex loads it when a task matches its description.

Can I use Deply Config in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Vashkatsi/deply --skill deply-config -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/deply-config, .gemini/skills/deply-config, .github/skills/deply-config and .opencode/skills/deply-config in your project.

What does Deply Config need to run?

SKILL.md names no scripts, command-line tools or credentials: Deply Config is instructions for the agent only. Our summary lists: Python 3.

Does Deply Config access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Deply Config safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Deply Config use?

Deply Config is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Deply Config use?

About 945 tokens (SKILL.md is roughly 3.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 6.4k tokens, read only when the agent opens those files.

What are the alternatives to Deply Config?

Skills that share tags, products or a category with Deply Config: Tbd (jlevy/strif, 131 stars), Light Project Structure (Light0305/Light-skills, 640 stars), Metaxy (anam-org/metaxy, 124 stars) and Claude Settings Audit (getsentry/skills, 1k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Deply Config?

Vashkatsi (a GitHub user) maintains it in Vashkatsi/deply, which has 173 GitHub stars. The repository was last updated on October 9, 2026.

Source: Vashkatsi/deply on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.