create-project-instructions

A skill for creating project-specific AGENTS.md files, which give coding agents instructions about a project’s context, roles, commands, phases, and working rules.

In plain words
What is it for?
Use it to generate or regenerate project-context AGENTS.md files after documenting the project, architecture, workflow, testing, and documentation needs.
Why use it?
It helps keep project instructions consistent and tailored to the repository and its current phase.

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/msiccdev/ai-context-kit/create-project-instructions
Any agent
npx skills add MSiccDev/ai-context-kit --skill create-project-instructions
Clone the repo
git clone --depth 1 https://github.com/MSiccDev/ai-context-kit

Made for: Claude Code, Codex.

Per session 25 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 615 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 $0.00025 $0.00615
Opus 5 $0.00013 $0.00308
Sonnet 5 $0.00005 $0.00123
Haiku 4.5 $0.00003 $0.00061

Measured 2d ago against content hash 4e389f2fd6f6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

create-project-instructions 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 2d 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/create-project-instructions/SKILL.md · 64 lines

How it starts

The opening of the file, as written. The whole thing — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Create Project Context AGENTS

Purpose

Generate project-context AGENTS.md files with required sections, role definitions, command namespace controls, and validation-ready structure.

When To Use

  • Use this skill when the task is to create or regenerate project-context AGENTS.md.
  • Use this skill when project context must include role/phase/style defaults.
  • Do not use this skill for user-context instruction generation.

How to Invoke

Load or attach this file's contents into your AI session to activate the workflow (paste, upload, or reference with #file:skills/create-project-instructions/SKILL.md in VS Code Copilot Chat). In Claude Projects, add it to project knowledge. See Invoking Skills in the README for full platform guidance.

Required Inputs

  • Project name, description, and current phase.
  • Tech stack, architecture, and repository structure.
  • Roles, default session state, and command namespace.
  • Objectives, testing strategy, and documentation standards.

Workflow

  1. Run phased discovery using references/discovery-phases.md.
  2. Apply required output schema from references/output-schema.md.
  3. Build command and role structures using:
    • references/command-template.md
    • references/role-template.md
  4. Apply artifact/summary contract from references/output-format.md.
  5. Stamp <!-- spec_version: 1.4.3 --> as an HTML comment at the top of the generated AGENTS.md.
  6. Validate completeness using references/quality-checklist.md before final output.

Output Expectations

  • One complete AGENTS.md file with all required project-context sections.
  • Session-state and command-reference elements are fully populated.
  • Core project-context required-section completeness is enforced through AGENTS structure.
  • Role definitions and examples are project-specific and actionable.
  • Output remains provider-neutral.
  • Output contract and summary format follow references/output-format.md.

Resources

  • Discovery workflow: references/discovery-phases.md
  • Output schema: references/output-schema.md
  • Command template: references/command-template.md
  • Role templates: references/role-template.md
  • Output contract: references/output-format.md
  • Quality checklist: references/quality-checklist.md
  • Structure baseline: ../../templates/AGENTS_template.md
  • Example reference: ../../AGENTS.md

Read the full file on GitHub · 64 lines

Files

What ships with it

7 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. 2d ago First seen · 64 lines · 25 tokens per session scan A 4e389f2fd6f6

Subscribe to this mod's changes

create-project-instructions is a skill published in the GitHub repository MSiccDev/ai-context-kit (12 stars, last pushed 4d ago), licensed MIT. It adds 25 tokens to every session and 615 once invoked, about $0.0001 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.