ac-tools-improve-agents-md

ac-tools-improve-agents-md is a skill for Claude Code from WaterplanAI/agentic-config. It costs 72 tokens per session (1,006 once invoked), scanned A, original, MIT.

A skill for generating and updating AGENTS.md, also known as CLAUDE.md, the file that records instructions for coding agents in a project. It detects the project type and fills in matching tooling details from templates.

In plain words
What is it for?
Bootstrapping or updating agent instructions, preserving existing custom content, and adding project-specific tools such as package managers and linters.
Why use it?
It avoids maintaining project instructions entirely by hand and keeps setup details consistent with the detected project type.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions CLAUDE.md; mentions AGENTS.md; mentions Gemini CLI.

Part of the agentic-config plugin — 49 skills, 1 plugin shipped together

Good fit Bootstrapping or updating agent instructions, preserving existing custom content, and adding project-specific tools such as package managers and linters.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/waterplanai/agentic-config/ac-tools-improve-agents-md
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add WaterplanAI/agentic-config --skill ac-tools-improve-agents-md
Clone the repo
git clone --depth 1 https://github.com/WaterplanAI/agentic-config

Made for: Claude Code.

Or install agentic-config, the plugin that ships this one along with the rest of its 49 skills, 1 plugin.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for ac-tools-improve-agents-md

README.md
[![agentmods](https://agentmods.dev/badge/skills/waterplanai/agentic-config/ac-tools-improve-agents-md/github.svg)](https://agentmods.dev/skills/waterplanai/agentic-config/ac-tools-improve-agents-md)
Your own site
<a href="https://agentmods.dev/skills/waterplanai/agentic-config/ac-tools-improve-agents-md"><img src="https://agentmods.dev/badge/skills/waterplanai/agentic-config/ac-tools-improve-agents-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for ac-tools-improve-agents-md

Your own site · 80×15
<a href="https://agentmods.dev/skills/waterplanai/agentic-config/ac-tools-improve-agents-md"><img src="https://agentmods.dev/badge/skills/waterplanai/agentic-config/ac-tools-improve-agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 72 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,006 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00072 $0.01006
Opus 5 $0.00036 $0.00503
Sonnet 5 $0.00014 $0.00201
Haiku 4.5 $0.00007 $0.00101

Measured 10d ago against content hash 074a1e7fe145, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

ac-tools-improve-agents-md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.

The scan reads SKILL.md. This mod also ships 4 executable files (tools/bootstrap.py, tools/preserve_custom.py, tools/project_type.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

packages/pi-ac-tools/skills/ac-tools-improve-agents-md/SKILL.md · 120 lines

How it starts

The opening of the file, as written. The whole thing — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.

improve-agents-md

Compatibility Note

This pi wrapper preserves the original setup/update workflow while expressing any confirmation points as explicit manual checkpoints in the current chat instead of assuming a runtime interactive-question primitive.

Generate and manage AGENTS.md (rendered as CLAUDE.md) using a single base template with dynamic tooling values from tooling.yml.

Architecture

assets/
  AGENTS.md.template     # Single base template with {{VAR}} placeholders
  tooling.yml            # Per-type tooling values (package_manager, linter, etc.)
  extras/pep723.md       # Optional section injected for Python types
  templates/shared/      # Shared templates (.gitignore)
tools/
  bootstrap.py           # Entrypoint: setup, update, validate
  template_engine.py     # Reads tooling.yml, renders template, injects extras
  project_type.py        # Auto-detect project type from file indicators
  preserve_custom.py     # Backup + CLAUDE.md migration detection

Modes

setup

Generate AGENTS.md for a project:

  1. Detect project type (or accept --type override)
  2. Back up existing files if --force
  3. Load tooling values from tooling.yml for detected type
  4. Render AGENTS.md.template with tooling substitution
  5. Inject extras (e.g., PEP 723 section for Python types)
  6. Write rendered AGENTS.md to project root
  7. Create CLAUDE.md and GEMINI.md as symlinks to AGENTS.md

update

Re-render AGENTS.md with latest template:

  1. Re-detect project type (or accept --type override)
  2. Preserve customizations if --force
  3. Re-render AGENTS.md with current tooling values

validate

Check AGENTS.md content:

  1. Verify AGENTS.md exists
  2. Check for unresolved {{VAR}} placeholders
  3. Verify required sections present
  4. Check CLAUDE.md is a symlink to AGENTS.md
  5. Warn if legacy PROJECT_AGENTS.md is present
  6. Check template assets exist

Flags

Flag Default Description
--dry-run false Print actions without executing
--force false Force overwrite (backup + re-render)
--type auto Override project type detection

Read the full file on GitHub · 120 lines

Files

What ships with it

8 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 10d ago First seen · 120 lines · 72 tokens per session scan A 074a1e7fe145

Subscribe to this mod's changes

ac-tools-improve-agents-md is a skill published in the GitHub repository WaterplanAI/agentic-config (30 stars, last pushed 1mo ago), licensed MIT. It adds 72 tokens to every session and 1,006 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.