Init

by mcollina72b727514771No licenseListed Oct 8, 2026Updated Oct 8, 2026

Creates, updates, or optimizes an AGENTS.md file for a repository with minimal, high-signal instructions covering non-discoverable coding conventions, tooling quirks, workflow preferences, and project-specific rules that agents cannot infer from reading the codebase. Use when setting up agent instructions or Claude configuration for a new repository, when an existing AGENTS.md is too long, generic, or stale, when agents repeatedly make avoidable mistakes, or when repository workflows have changed and the agent configuration needs pruning. Applies a discoverability filter—omitting anything Claude can learn from README, code, config, or directory structure—and a quality gate to verify each line remains accurate and operationally significant.

Instructions onlyAI & Agents
AI-generated overview

Creates, updates, or prunes an AGENTS.md file with only non-discoverable, high-signal instructions for coding agents.

What it does
This skill guides the creation, updating, or pruning of an AGENTS.md file for a repository. It applies a discoverability filter, keeping only guidance that agents cannot infer from the README, code, config, or directory structure, and a quality gate that checks each line for accuracy and operational significance. It recommends short sections such as scope and routing, non-discoverable commands, landmines, and task-specific constraints, and suggests hierarchical AGENTS.md files for large repositories. It produces a leaner, more accurate AGENTS.md rather than a codebase overview.
When to use it
Use it when setting up agent instructions for a new repository, or when an existing AGENTS.md is too long, generic, or stale. It also fits when agents repeatedly make avoidable mistakes or when repository workflows have changed and the guidance needs pruning.
Requirements
No scripts or special tooling; it is instructions only. It works best when the agent can read repository files such as AGENTS.md, README.md, PROJECT.md, Cursor rules, Copilot instructions, GEMINI.md, and CI or package manager configuration.

When to use

Use this skill when creating or updating AGENTS.md for a repository.

Use it especially when:

  • the current AGENTS.md is long, generic, or stale
  • agents repeatedly make the same avoidable mistakes
  • repository workflows changed and agent guidance needs pruning

Instructions

Treat AGENTS.md as a living list of non-discoverable landmines and workflow gotchas, not a codebase overview.

Core rule: discoverability filter

Before adding any line, ask:

Can an agent discover this by reading the repo (README, code, config, scripts, directory tree)?

  • If yes: do not include it in AGENTS.md.
  • If no, and it materially affects task success/cost/safety: include it.

What earns a line

Include only guidance that is:

  1. Non-discoverable from repository files alone
  2. Operationally significant (changes commands, outcomes, or safety)
  3. Actionable (specific enough to execute)

Typical examples:

  • Non-standard tooling choices (e.g. use uv instead of pip)
  • Command caveats (e.g. tests must run with --no-cache due to fixture behavior)
  • Hidden constraints/landmines (deprecated directories still imported in production)
  • Critical local conventions that are not encoded in lint/tests/config

What to remove or avoid

Do not include:

  • Tech stack summaries
  • Directory structure overviews
  • Architecture descriptions agents can infer from code
  • Generic best-practice advice
  • Rules already enforced by tooling (linters, typecheck, tests, CI)
  • Mandatory boilerplate headers unless the repo explicitly requires one

Recommended structure

Prefer short, high-signal sections such as:

  • Scope & routing (which areas need separate/module-local AGENTS files)
  • Non-discoverable commands
  • Landmines / do-not-touch areas
  • Task-specific constraints

For large repos, recommend hierarchical AGENTS.md files near relevant modules instead of one monolithic root file.

Source files to check first

  • Existing AGENTS.md
  • README.md
  • PROJECT.md (if present)
  • Cursor rules (.cursor/rules/ or .cursorrules)
  • Copilot instructions (.github/copilot-instructions.md)
  • GEMINI.md
  • CI/workflow files and package manager config (for command/tooling mismatches)

If AGENTS.md exists, improve it incrementally instead of replacing it blindly.

Maintenance mindset

AGENTS.md is temporary guidance, not permanent configuration.

When recurring issues appear:

  1. Prefer fixing the root cause in code/tooling (lint rule, test, script, structure)
  2. Keep only the minimum instruction needed until the root cause is solved
  3. Prune stale instructions aggressively

Quality gate before finalizing

For each line in AGENTS.md, verify:

  • Is it non-discoverable?
  • Is it still accurate today?
  • Does it materially reduce mistakes/cost/time?

Delete any line that fails one of these checks.

Source and attribution

Source:mcollina/skillsinskills/initat commit72b7275

License: No license

Content belongs to its original authors. SourceWeft indexes it from a public repository.

Report or request removal