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/dean0x/devflow/claude-mdgit clone --depth 1 https://github.com/dean0x/devflowWhat 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 | $0.10907 | $0.10907 |
| Opus 5 | $0.05454 | $0.05454 |
| Sonnet 5 | $0.02181 | $0.02181 |
| Haiku 4.5 | $0.01091 | $0.01091 |
Grade B, and why
devflow CLAUDE.md 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 2d 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.
**Debug Tracing**: Single global toggle covering all hooks. Enabled via `devflow debug --enable/--disable/--status` CLI or by setting `DEVFLOW_HOOK_DEBUG=1` in `~/.claude/settings.json` env block (survives reinstalls). A How it starts
The opening of the file, as written. The whole thing — 296 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Devflow Development Guide
Instructions for developers and AI agents working on Devflow. For user docs, see README.md.
Purpose
Devflow enhances Claude Code with intelligent development workflows. Modifications must:
- Maintain brutal honesty in review outputs (no sycophancy)
- Preserve context across sessions
- Enhance developer empowerment without replacing judgment
- Ensure all commands are self-documenting
Architecture Overview
Registry-driven CLI tool with 21 plugins (12 core + 9 optional). Plugins are entries in DEVFLOW_PLUGINS in src/core/plugins.ts — each entry declares its commands, agents, skills, and rules arrays. All assets live once in src/assets/ and install directly; the only compile step is .mds command sources → dist/commands/ via npm run build:mds.
| Plugin | Purpose |
|---|---|
devflow-implement |
Complete task implementation lifecycle |
devflow-plan |
Unified design planning with gap analysis |
devflow-code-review |
Comprehensive code review |
devflow-resolve |
Review issue resolution |
devflow-debug |
Competing hypothesis debugging |
devflow-explore |
Codebase exploration with knowledge base creation |
devflow-research |
Multi-type research with trust-aware synthesis |
devflow-release |
Adaptive project release with learned configuration |
devflow-self-review |
Self-review (Simplify + Scrutinize) |
devflow-bug-analysis |
Proactive bug finding with static and semantic analysis |
devflow-ambient |
Ambient mode — orchestrator charter + plan handoff |
devflow-core-skills |
Auto-activating quality enforcement |
devflow-dynamic |
Dynamic workflow recipes — dependency-aware tickets→plan→build delivery pipeline (optional) |
devflow-typescript |
TypeScript language patterns (optional) |
devflow-react |
React framework patterns (optional) |
devflow-accessibility |
Web accessibility patterns (optional) |
devflow-ui-design |
UI design patterns (optional) |
devflow-go |
Go language patterns (optional) |
devflow-python |
Python language patterns (optional) |
devflow-java |
Java language patterns (optional) |
devflow-rust |
Rust language patterns (optional) |
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.
- 2d ago First seen · 296 lines · 10,907 tokens per session scan B 74f1868abdf1
devflow CLAUDE.md is an instructions file published in the GitHub repository dean0x/devflow (19 stars, last pushed 2d ago), licensed MIT. It adds 10,907 tokens to every session, about $0.0545 per session on Opus 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.
Other instructions, from other repositories
opencode-ensemble AGENTS.md
AGENTS.md instructions for hueyexe/opencode-ensemble, covering opencode-ensemble — agent guidelines, what this is, design context, users and brand personality.
herdmates CLAUDE.md
Instructions for caioniehues/herdmates, covering claude.md — project context for claude code, read in this order, hard rules, environment note and reference material in-repo.
statsclaw CLAUDE.md
Instructions for statsclaw/statsclaw, a project described as: A workflow framework for statistical package development.
siegard-code CLAUDE.md
Instructions for zig999/siegard-code, covering claude.md — ai first agent lab (v2), project purpose, project structure, directory rules and installation (manual copy).
agent-teams-ai CLAUDE.md
Claude Code instructions for 777genius/agent-teams-ai, covering agent teams, tech stack, commands, git commits and path aliases.
competitive-intelligence-radar CLAUDE.md
Instructions for sabahudin-web/competitive-intelligence-radar, covering claude.md, what this project is, first thing to do in a fresh checkout, architecture you must respect and hard rules (these are not optional).