compose-agents-md

A guided tool for creating an AGENTS.md file, which gives coding agents project-specific instructions. It helps choose a profile or assemble instructions from smaller reusable sections.

In plain words
What is it for?
Use it to describe the project, select a suitable profile, combine language and architecture guidance, and compose AGENTS.md.
Why use it?
It helps a new project get consistent agent guidance without requiring you to design the instruction file from scratch.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/soulcodex/agentic/compose-agents-md
Any agent
npx skills add soulcodex/agentic --skill compose-agents-md
Clone the repo
git clone --depth 1 https://github.com/soulcodex/agentic

Made for: Claude Code, Codex.

Per session 78 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 560 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00078 $0.00560
Opus 5 $0.00039 $0.00280
Sonnet 5 $0.00016 $0.00112
Haiku 4.5 $0.00008 $0.00056

Measured 3d ago against content hash e20ba341aa05, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

compose-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 3d ago.

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.

skills/agentic/compose-agents-md/SKILL.md · 77 lines

What it actually says

Compose AGENTS.md Skill

Help the user create an AGENTS.md for their project.

Step 1 — Understand the Project

Ask (if not already known):

  1. What language(s) does the project use?
  2. What architectural pattern (hexagonal, microservices, BFF, monolith)?
  3. What is the primary purpose of the project?
  4. Which AI vendors are used on this project?

Step 2 — Recommend a Profile

Check just list-profiles to show available profiles.

Match the user's answers to an existing profile. If a match exists:

just compose {profile-name} {/path/to/target-project}

If no profile matches closely enough, offer to: a) Compose from individual fragments (guided selection) b) Create a new profile for this project type

Step 3 — Fragment Selection (if no profile matches)

Guide the user through selecting fragments:

Base fragments (always recommended):

  • git-conventions — always include
  • security — always include
  • code-review — include if team does code reviews
  • testing-philosophy — include if testing standards matter
  • documentation — include if docs standards matter

Language: pick from agents/languages/ Architecture: pick from agents/architecture/ Practices: pick from agents/practices/ Domain: pick from agents/domains/ if a match exists

Step 4 — Compose and Deploy

Run the compose and vendor-gen commands:

just compose {profile-or-custom} {target-path}
just vendor-gen {target-path}

Step 5 — Verify

Open {target-path}/AGENTS.md with the user and confirm:

  • The content accurately represents the project's standards
  • Build/test/lint commands are correct
  • No placeholder tokens ({{TOKEN}}) remain unfilled
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. 3d ago First seen · 77 lines · 78 tokens per session scan A e20ba341aa05

Subscribe to this mod's changes

compose-agents-md is a skill published in the GitHub repository soulcodex/agentic (10 stars, last pushed 3d ago), licensed MIT. It adds 78 tokens to every session and 560 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 2026-08-31.

Related

Other skills, from other repositories

design-debt-audit

Inventory and prioritise accumulated design inconsistencies across a product. Use when drift has built up over time. For token coverage specifically use design-token-audit (designer-toolkit); for WCAG gaps use accessibility-audit (design-systems).

Owl-Listener/designer-skills · 59 tokens

design-impact-reporting

Communicate design's contribution to business and user outcomes in stakeholder language. Use when reporting results upward. For choosing the metrics in the first place, use metrics-definition (ux-strategy).

Owl-Listener/designer-skills · 44 tokens

research-repository

Build a repository that makes findings findable, reusable, and cumulative across teams. Use when the same research keeps getting redone. For synthesising one study, use affinity-diagram.

Owl-Listener/designer-skills · 43 tokens

survey-design

Design unbiased survey instruments — question wording, scales, and sampling — to measure attitudes at scale. Use when you need quantitative breadth. For behavioural experiments, use a-b-test-design (prototyping-testing).

Owl-Listener/designer-skills · 47 tokens

design-system-governance

Define how the system evolves — contribution model, versioning, deprecation, and change management. Use when multiple teams contribute. For driving uptake use design-system-adoption (designer-toolkit); for design file history use version-control-strategy (design-ops).

Owl-Listener/designer-skills · 62 tokens

localization-design

Design for multiple languages, writing directions, and cultural contexts — text expansion, RTL mirroring, and locale formats. Use when shipping beyond one locale. For the words themselves, use ux-writing (designer-toolkit).

Owl-Listener/designer-skills · 49 tokens