mcpField
I
init

init

github.com/mcollinaAgent workflows2.0k1.3k installsUpdated 2w ago
Repository

About init

A skill for creating or revising repository `AGENTS.md` files. It focuses guidance on actionable, operationally significant details that cannot be inferred from repository files, and encourages pruning stale instructions.

Key features

  1. 01Filters for non-discoverable guidance
  2. 02Identifies operational constraints
  3. 03Suggests concise section structure
  4. 04Reviews existing instructions
  5. 05Prunes stale guidance

Use cases

  1. 01Creating repository `AGENTS.md` files
  2. 02Removing generic agent instructions
  3. 03Recording hidden workflow constraints
  4. 04Updating guidance after workflow changes

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/mcollina/skills --skill init

After installing, type/initin Claude Code to confirm it loaded.

Bundled filestile.json

Details

From the project README

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.

Comments

Markdown supported