TÂCHES Claude Code Resources is a collection of custom commands, skills, and agents that structure Claude Code workflows such as planning, debugging, automation, and subagent creation. It is intended for developers who use Claude Code for real software projects. The catalogue entries are examples of the resources included in the collection.
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.
git clone --depth 1 https://github.com/glittercowboy/taches-cc-resourcesWrote 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/glittercowboy/taches-cc-resources/ask-me-questions)<a href="https://agentmods.dev/commands/glittercowboy/taches-cc-resources/ask-me-questions"><img src="https://agentmods.dev/badge/commands/glittercowboy/taches-cc-resources/ask-me-questions/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.
<a href="https://agentmods.dev/commands/glittercowboy/taches-cc-resources/ask-me-questions"><img src="https://agentmods.dev/badge/commands/glittercowboy/taches-cc-resources/ask-me-questions.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00009 | $0.00760 |
| Opus 5 | $0.00005 | $0.00380 |
| Sonnet 5 | $0.00002 | $0.00152 |
| Haiku 4.5 | $0.00001 | $0.00076 |
Grade A, and why
ask-me-questions 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 12d 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.
What it actually says
This prevents premature execution, captures nuance, and creates a collaborative context-building flow where you maintain control over when work begins.
<intake_gate>
<no_context_handler> IF $ARGUMENTS is empty or vague: → IMMEDIATELY use AskUserQuestion with:
- header: "Task"
- question: "What would you like help with?"
- options:
- "Write something" - Create a document, email, post, or other written content
- "Build something" - Create code, a feature, system, or technical artifact
- "Figure something out" - Research, analyze, or help me think through a problem
- "Other" - Something else entirely
Then proceed to context_analysis with their response.
IF $ARGUMENTS provides clear context: → Skip to context_analysis </no_context_handler>
<context_analysis> Analyze $ARGUMENTS (or conversation context) to extract what's already provided:
- What: The task, deliverable, or outcome requested
- Who: Target audience, recipient, or stakeholders
- Why: Purpose, goal, or motivation
- How: Approach, constraints, or requirements
- When: Timeline, urgency, or dependencies
Only ask about genuine gaps - don't re-ask what's already stated. </context_analysis>
<initial_questions> Use AskUserQuestion to ask 2-4 questions based on actual gaps:
If "what" is unclear:
- "What specifically do you want?" with domain-appropriate options
If "who" is unclear:
- "Who is this for?" with options: Myself, My team, External stakeholders, Public audience, Other
If "why" is unclear:
- "What's the goal?" with options relevant to the task type
If "how" is unclear:
- "Any constraints or preferences?" with domain-appropriate options
Skip questions where the context already provides the answer. </initial_questions>
<decision_gate> After receiving answers, use AskUserQuestion:
Question: "Ready to proceed, or would you like me to ask more questions?"
Options:
- Start working - I have enough context, proceed with the task
- Ask more questions - There are details I want to clarify
- Let me add context - I want to provide additional information
If "Ask more questions" → generate 2-3 contextual follow-ups based on accumulated context, then present decision gate again If "Let me add context" → receive input, then present decision gate again If "Start working" → proceed to execution </decision_gate>
</intake_gate>
<success_criteria>
- No questions asked about information already provided
- User maintains control over when execution begins
- Context accumulates through multiple rounds if needed
- All AskUserQuestion calls use structured options (not plain text questions)
- Task executes only after user explicitly chooses to proceed </success_criteria>
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.
- 12d ago First seen · 94 lines · 9 tokens per session scan A 465dfbed1238
ask-me-questions is a command published in the GitHub repository glittercowboy/taches-cc-resources (1,976 stars, last pushed 5mo ago), licensed MIT. It adds 9 tokens to every session and 760 once invoked, about $0.0000 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.
Other commands, from other repositories
report
Generate a project analytics report covering code quality, velocity, and health metrics.
explain
Explain a code file, function, or concept in clear, structured language.
env-setup
Set up environment configuration files from templates with validation.
debug-pod
Debug a failing or unhealthy Kubernetes pod by analyzing events, logs, and configuration.
document-all
Auto-document the entire codebase by generating module-level docs, function signatures, and API references.
fix-comments
Address PR review comments by implementing requested changes automatically.