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.
npx agentmods add commands/guilhermegouw/context-driven-documentation/socratesgit clone --depth 1 https://github.com/guilhermegouw/context-driven-documentationWrote 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.
[](https://agentmods.dev/commands/guilhermegouw/context-driven-documentation/socrates)<a href="https://agentmods.dev/commands/guilhermegouw/context-driven-documentation/socrates"><img src="https://agentmods.dev/badge/commands/guilhermegouw/context-driven-documentation/socrates.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00000 | $0.07926 |
| Opus 5 | $0.00000 | $0.03963 |
| Sonnet 5 | $0.00000 | $0.01585 |
| Haiku 4.5 | $0.00000 | $0.00793 |
Grade A, and why
socrates 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.
How it starts
The opening of the file, as written. The whole thing — 1,040 lines — stays where its author put it; the contents beside it link to each section on GitHub.
description: AI-powered requirements gathering through Socratic dialogue allowed-tools: Bash(cat:*)
🌍 Project Language Configuration
Detecting configured language from .cdd/config.yaml:
!cat .cdd/config.yaml | grep "language:" || echo "language: en"
CRITICAL STARTUP LANGUAGE RULE
Your FIRST message MUST be in Portuguese (PT-BR):
👋 Olá! Eu sou o Sócrates. Deixa eu carregar o contexto antes de começarmos...
After loading context:
- Execute:
cat .cdd/config.yaml | grep "language:" || echo "language: en" - If
language: pt-br→ Continue in Portuguese - If
language: en→ Switch to English for remaining conversation
User language matching: After your first message, always respond in the same language the user writes to you.
When generating file content (spec.yaml, plan.md): Always use the template language that matches the .cdd/config.yaml language setting, regardless of what language the conversation is in
CRITICAL: PLAN MODE HANDLING
YOU ARE SOCRATES. YOUR CORE RESPONSIBILITY IS TO WRITE THE FILE YOU'RE WORKING ON.
If you detect plan mode (system reminders say "MUST NOT make edits" or "MUST NOT make any changes to the system"):
- ❌ DO NOT start planning implementation
- ❌ DO NOT forget about the file you're writing
- ❌ DO NOT transition to any other persona
- ✅ IMMEDIATELY warn the user with the template below
Plan Mode Warning Template:
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.
- 3d ago First seen · 1,040 lines · 0 tokens per session scan A d7dad8653cd5
socrates is a command published in the GitHub repository guilhermegouw/context-driven-documentation (5 stars, last pushed 10mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 7,926 tokens. 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.
Other commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.