create-usercontext-instructions

Um processo para criar ficheiros de instruções que descrevem o contexto de uma pessoa. Organiza informações como perfil técnico, projetos, objetivos, preferências e limites num formato definido.

In plain words
What is it for?
Serve para criar ou recriar um ficheiro de contexto do utilizador com uma estrutura adequada para ser reutilizada por agentes de programação.
Why use it?
Ajuda a reunir o contexto de forma consistente e reduz o risco de esquecer informações importantes. Também considera como tratar dados pessoais e sensíveis.

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

Made for: Claude Code, Codex.

Per session 22 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 567 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 $0.00022 $0.00567
Opus 5 $0.00011 $0.00283
Sonnet 5 $0.00004 $0.00113
Haiku 4.5 $0.00002 $0.00057

Measured 2d ago against content hash 4816f1219011, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

create-usercontext-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-usercontext-instructions/SKILL.md · 60 lines

How it starts

The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Create User Context Instructions

Purpose

Generate a complete user-context instruction file with required sections, privacy-aware content handling, and consistent output formatting.

When To Use

  • Use this skill when the task is to create or regenerate a *_usercontext.instructions.md file.
  • Use this skill when user context must be gathered through structured phases.
  • Do not use this skill for project AGENTS.md (project context) files.

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-usercontext-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

  • Target identity label and role/title.
  • Privacy expectations (full detail vs placeholders).
  • Technical profile, projects, goals, style, and constraints.
  • Desired output filename/path.

Workflow

  1. Run phased discovery using references/discovery-phases.md.
  2. Normalize findings into required schema using references/output-schema.md.
  3. Apply format contract from references/output-format.md.
  4. Stamp spec_version: "1.4.3" in the YAML frontmatter of the generated artifact.
  5. Validate against references/quality-checklist.md before final output.
  6. If structured metadata is requested, apply references/json-metadata-schema.md.

Output Expectations

  • One complete *.instructions.md file for user context.
  • Required section coverage and logical ordering are preserved.
  • Privacy handling is explicit and consistent.
  • Output is 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
  • Optional metadata schema: references/json-metadata-schema.md
  • Output contract: references/output-format.md
  • Quality checklist: references/quality-checklist.md
  • Structure baseline: ../../templates/usercontext_template.instructions.md
  • Example reference: ../../usercontexts/sample_usercontext.instructions.md

Read the full file on GitHub · 60 lines

Files

What ships with it

6 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 · 60 lines · 22 tokens per session scan A 4816f1219011

Subscribe to this mod's changes

create-usercontext-instructions is a skill published in the GitHub repository MSiccDev/ai-context-kit (12 stars, last pushed 4d ago), licensed MIT. It adds 22 tokens to every session and 567 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.