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.
npx skills add glittercowboy/taches-cc-resources --skill create-mcp-serversgit 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/skills/glittercowboy/taches-cc-resources/create-mcp-servers)<a href="https://agentmods.dev/skills/glittercowboy/taches-cc-resources/create-mcp-servers"><img src="https://agentmods.dev/badge/skills/glittercowboy/taches-cc-resources/create-mcp-servers/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/skills/glittercowboy/taches-cc-resources/create-mcp-servers"><img src="https://agentmods.dev/badge/skills/glittercowboy/taches-cc-resources/create-mcp-servers.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 | $0.00058 | $0.01310 |
| Opus 5.5 | $0.00023 | $0.00524 |
| Sonnet 5.5 | $0.00012 | $0.00262 |
| Haiku 4.5 | $0.00006 | $0.00131 |
Grade B, and why
create-mcp-servers scanned grade B with 1 finding 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 2mo 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
**Server not appearing:** Check `claude mcp list`, verify config in `~/.claude/settings.json` How it starts
The opening of the file, as written. The whole thing — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.
<essential_principles>
<the_5_rules> Every MCP server must follow these:
- Never Hardcode Secrets - Use
${VAR}expansion in configs, environment variables in code - Use
cwdProperty - Isolates dependencies (not--cwdin args) - Always Absolute Paths -
which uvto find paths, never relative - One Server Per Directory -
~/Developer/mcp/{server-name}/ - Use
uvfor Python - Better than pip, handles venvs automatically </the_5_rules>
<security_checklist>
- Never ask user to paste secrets into chat
- Always use environment variables for credentials
- Use ${VAR} expansion in configs
- Provide exact commands for user to run in terminal
- Verify environment variable existence without showing values
- Never hardcode API keys in code or configs </security_checklist>
<architecture_decision> Operation count determines architecture:
- 1-2 operations → Traditional pattern (flat tools)
- 3+ operations → On-demand discovery pattern (meta-tools)
Traditional: Each operation is a separate tool On-demand: 4 meta-tools (discover, get_schema, execute, continue) + operations.json </architecture_decision>
Standard location: ~/Developer/mcp/{server-name}/
</essential_principles>
No context provided (skill invoked without description): Use AskUserQuestion:
- header: "Mode"
- question: "What would you like to do?"
- options:
- "Create a new MCP server" → workflows/create-new-server.md
- "Update an existing MCP server" → workflows/update-existing-server.md
- "Troubleshoot a server" → workflows/troubleshoot-server.md
Context provided (user described what they want): Route directly to workflows/create-new-server.md
<workflows_index>
| Workflow | Purpose |
|---|---|
| create-new-server.md | Full 8-step workflow from intake to verification |
| update-existing-server.md | Modify or extend an existing server |
| troubleshoot-server.md | Diagnose and fix connection/runtime issues |
| </workflows_index> |
<templates_index>
| Template | Purpose |
|---|---|
| python-server.py | Traditional pattern starter for Python |
| typescript-server.ts | Traditional pattern starter for TypeScript |
| operations.json | On-demand discovery operations definition |
| </templates_index> |
<scripts_index>
| Script | Purpose |
|---|---|
| setup-python-project.sh | Initialize Python MCP project with uv |
| setup-typescript-project.sh | Initialize TypeScript MCP project with npm |
| </scripts_index> |
<references_index> Core workflow:
- creation-workflow.md - Complete step-by-step with exact commands
Architecture patterns:
- traditional-pattern.md - For 1-2 operations (flat tools)
- large-api-pattern.md - For 3+ operations (on-demand discovery)
Language-specific:
- python-implementation.md - Async patterns, type hints
- typescript-implementation.md - Type safety, SDK features
Advanced topics:
- oauth-implementation.md - OAuth with stdio isolation
- response-optimization.md - Field truncation, pagination
- tools-and-resources.md - Resources API, prompts, streaming
- testing-and-deployment.md - Unit tests, packaging, publishing
- validation-checkpoints.md - All validation checks
- adaptive-questioning-guide.md - Question templates for intake
- api-research-template.md - API research document format </references_index>
<quick_reference>
# List servers
claude mcp list
# Add server (Python)
claude mcp add --transport stdio <name> \
--env API_KEY='${API_KEY}' \
-- uv --directory ~/Developer/mcp/<name> run python -m src.server
# Add server (TypeScript)
claude mcp add --transport stdio <name> \
--env API_KEY='${API_KEY}' \
-- node ~/Developer/mcp/<name>/build/index.js
# Remove server
claude mcp remove <name>
# Check logs
tail -f ~/Library/Logs/Claude/mcp-server-<name>.log
# Find paths
which uv && which node && which python
</quick_reference>
What ships with it
22 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.
- references/adaptive-questioning-guide.md 1.1 KB
- references/api-research-template.md 1.8 KB
- references/auto-installation.md 10 KB
- references/best-practices.md 59 KB
- references/creation-workflow.md 19 KB
- references/large-api-pattern.md 19 KB
- references/oauth-implementation.md 8.7 KB
- references/python-implementation.md 18 KB
- references/response-optimization.md 16 KB
- references/testing-and-deployment.md 16 KB
- references/tools-and-resources.md 18 KB
- references/traditional-pattern.md 12 KB
- references/typescript-implementation.md 13 KB
- references/validation-checkpoints.md 3.0 KB
- scripts/setup-python-project.sh 1.3 KB runs code
- scripts/setup-typescript-project.sh 2.0 KB runs code
- templates/operations.json 2.9 KB
- templates/python-server.py 4.7 KB runs code
- templates/typescript-server.ts 4.5 KB runs code
- workflows/create-new-server.md 9.1 KB
- workflows/troubleshoot-server.md 3.3 KB
- workflows/update-existing-server.md 2.4 KB
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.
- 2mo ago First seen · 166 lines · 58 tokens per session scan B c774949f6c1b
create-mcp-servers is a skill published in the GitHub repository glittercowboy/taches-cc-resources (1,989 stars, last pushed 7mo ago), licensed MIT. It adds 58 tokens to every session and 1,310 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
create-mcp-servers compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| create-mcp-serversglittercowboy/taches-cc-resources | Skill | 2.0k | 7mo ago | MIT | B | 58 | Claude Code |
| api-security-best-practiceslingxling/awesome-skills-cn | Skill | 334 | 1mo ago | MIT | A | 29 | Claude Code |
| oracle-adkfrankxai/claude-skills-library | Skill | 47 | yesterday | MIT | A | 50 | Claude Code |
| langgraph-patternsfrankxai/claude-skills-library | Skill | 47 | yesterday | MIT | A | 53 | Claude Code |
| api-patternslingxling/awesome-skills-cn | Skill | 334 | 1mo ago | MIT | A | 28 | Claude Code |
| amazon-alexalingxling/awesome-skills-cn | Skill | 334 | 1mo ago | MIT | A | 53 | Claude Code |
| debridgesendaifun/skills | Skill | 130 | 3mo ago | Apache-2.0 | A | 48 | Claude Code, Codex |