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 instructions/cocaxcode/devflow-mcp/claude-mdgit clone --depth 1 https://github.com/cocaxcode/devflow-mcpWhat 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 | $0.01018 | $0.01018 |
| Opus 5 | $0.00509 | $0.00509 |
| Sonnet 5 | $0.00204 | $0.00204 |
| Haiku 4.5 | $0.00102 | $0.00102 |
Grade A, and why
devflow-mcp CLAUDE.md 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 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.
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 — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — @cocaxcode/devflow-mcp
Project Overview
MCP server that connects Jira (Cloud + Server) with GitHub/GitLab to automate dev workflows. Branch creation, issue transitions, PR/MR generation, custom flow playbooks, and configurable rules. 32 tools.
Stack
- TypeScript 5.x (strict mode, ESM)
- @modelcontextprotocol/sdk 1.27.x (unified package)
- Zod 3.25+ for schema validation
- yaml 2.7+ for YAML parsing
- Vitest for testing
- tsup for building (ESM output with shebang,
__PKG_VERSION__define)
Architecture
src/
├── index.ts # Entry point (shebang + StdioServerTransport)
├── server.ts # createServer(storageDir?) factory + INSTRUCTIONS
├── tools/ # MCP tool registration (one file per group)
│ ├── project.ts # df_project_setup/update/list/switch/delete (5)
│ ├── jira.ts # df_issues/issue/statuses/transition/assign/comment (6)
│ ├── git.ts # df_branch/find_branch/checkout/pull/merge/push/pr (7)
│ ├── flow.ts # df_flow_create/list/get/update/delete (5)
│ └── rule.ts # df_rule_create/list/get/update/toggle/delete/project_override/project_add/project_remove (9)
├── lib/
│ ├── types.ts # Shared TypeScript interfaces
│ ├── storage.ts # JSON file storage in ~/.devflow-mcp/
│ ├── git-exec.ts # Shell git command execution
│ ├── git/
│ │ ├── factory.ts # createGitProvider() factory
│ │ ├── detect.ts # Auto-detect Git provider from remote
│ │ ├── github.ts # GitHub REST API client
│ │ └── gitlab.ts # GitLab REST API client
│ └── jira/
│ └── client.ts # Jira REST API client (Cloud + Server)
Key Patterns
- Factory function:
createServer(storageDir?)for testability - SDK imports: Deep paths —
@modelcontextprotocol/sdk/server/mcp.js - Tool API:
.tool(name, description, schema, handler)with raw Zod shapes (NOT z.object) - Error handling: Return
{ isError: true }, never throw from tool handlers - Logging: ONLY
console.error()— stdout is reserved for JSON-RPC - Storage: JSON files in
~/.devflow-mcp/, configurable via env - Confirm pattern: Destructive tools (df_transition, df_branch, df_push, df_merge) require
confirm: true - Git provider factory: Auto-detects GitHub vs GitLab from remote URL
- Instructions field: Server provides behavioral guidance to AI clients
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 First seen · 96 lines · 1,018 tokens per session scan A e29088cabf2a
devflow-mcp CLAUDE.md is an instructions file published in the GitHub repository cocaxcode/devflow-mcp (1 stars, last pushed 5mo ago), licensed MIT. It adds 1,018 tokens to every session, about $0.0051 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 2026-08-31.
Other instructions, from other repositories
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
buildNext
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
spec-kit AGENTS.md
Instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
langchain AGENTS.md
Instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.