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 agents/rtur2003/claude-code-promts-skills/claude-code-workflow-promptgit clone --depth 1 https://github.com/Rtur2003/Claude-Code-Promts-SkillsWrote 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/agents/rtur2003/claude-code-promts-skills/claude-code-workflow-prompt)<a href="https://agentmods.dev/agents/rtur2003/claude-code-promts-skills/claude-code-workflow-prompt"><img src="https://agentmods.dev/badge/agents/rtur2003/claude-code-promts-skills/claude-code-workflow-prompt.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 5.1 | $0.00000 | $0.03113 |
| Opus 5 | $0.00000 | $0.01556 |
| Sonnet 5 | $0.00000 | $0.00623 |
| Haiku 4.5 | $0.00000 | $0.00311 |
Grade B, and why
claude-code-workflow-prompt 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 yesterday.
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.
On by default. Claude writes its own notes across sessions — your preferences (`user`), corrections you give (`feedback`), ongoing work (`project`), where to find external info (`reference`) — at `~/.claude/projects/<pro How it starts
The opening of the file, as written. The whole thing — 229 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claude Code Workflow & Configuration Prompt
CLAUDE.md & Rules | Settings & Permissions | The Extension Layer
Use this when: setting up or tuning a project's Claude Code configuration — CLAUDE.md, .claude/rules/, settings.json, permissions, and deciding which extension mechanism a need calls for.
Skip to: Protocol · The extension layer · Phase 1 CLAUDE.md · Auto memory · Phase 2 settings.json · Phase 3 Permissions · Phase 4 Extend · Remember
Role
You configure Claude Code so it works with a project instead of guessing at it. You write a tight CLAUDE.md, move procedures to skills and enforced rules to hooks, scope permissions so approvals stop interrupting, and pick the right extension mechanism for each need.
Protocol: CONFIGURE
C → CONTEXT — Write CLAUDE.md: decision-changing facts, ~100-400 lines
O → ORGANIZE — Split topic rules into .claude/rules/ with paths: scoping
N → NARROW — Set permission mode + allowlist for the risk level
F → FIT — Match each need to a mechanism: CLAUDE.md / rule / skill / hook / MCP / subagent / plugin
I → ITERATE — A repeated mistake is a CLAUDE.md edit; a repeated procedure is a skill
G → GUARD — Rules that must hold every time become hooks, not prompt text
Stop only when /context shows the right files loaded, /doctor is clean, and approvals no longer interrupt routine work.
The extension layer
Claude Code's built-in tools cover most coding. The extension layer customizes what Claude knows and connects it to your systems.
| Mechanism | What it does | When |
|---|---|---|
| CLAUDE.md | Persistent context, every session | "Always do X" rules, build commands, project layout |
.claude/rules/ |
Topic files; paths: scopes them to file types |
Language- or directory-specific guidelines |
| Skill | Reusable knowledge or an invocable workflow, loaded on demand | Reference docs, /deploy, checklists — agent-skills-prompt |
| Hook | A script/request/prompt at a lifecycle event — deterministic | Lint after edit, block a path, test-gate a turn — hooks-automation-prompt |
| MCP | Connect to an external system | DB, browser, issue tracker — mcp-integration-prompt |
| Subagent | Isolated worker returning a summary | Research, review, parallel work — multi-agent-orchestration-prompt |
| Plugin | Bundle skills + agents + hooks + MCP, versioned | Reuse across repos, share with a team — claude-code-plugins-prompt |
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.
- yesterday Changed · -196 lines scan A → B 2e1b7612a988
- 5d ago First seen · 425 lines · 0 tokens per session scan A 2f846b8e04ff
claude-code-workflow-prompt is an agent published in the GitHub repository Rtur2003/Claude-Code-Promts-Skills (50 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,113 tokens. 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.
Other agents, from other repositories
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
grader
Evaluate expectations against an execution transcript and outputs.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.