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/dhananjay625/dev-workflow/agents-mdgit clone --depth 1 https://github.com/Dhananjay625/dev-workflowWhat 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 | $0.02408 | $0.02408 |
| Opus 5 | $0.01204 | $0.01204 |
| Sonnet 5 | $0.00482 | $0.00482 |
| Haiku 4.5 | $0.00241 | $0.00241 |
Grade A, and why
dev-workflow AGENTS.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 — 206 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Workflow Rules
Rules for any AI coding agent working in this repository (Codex, Gemini CLI, Cursor, Aider, Claude Code without the plugin, or any other). Follow them without being asked. They are tool-agnostic: no specific agent features are required, only the ability to read files, run commands, and follow instructions.
(If you are Claude Code with the dev-workflow plugin installed, the plugin already enforces these rules with hooks and subagents - this file is the fallback and the shared contract; the two never conflict.)
1. Session continuity (do this first, every session)
- FIRST ACTION: locate and read the project's
CHANGELOG.md. Check the current directory, then search downward (excluding node_modules/.git). In a monorepo, the changelog next to the files being edited is the project's memory - never create a second one at a higher level, which would split it.- The
## Current stateblock at the top says exactly where the last session stopped: what works, what's broken, the next step, open decisions, and known dead ends. Resume from it. Never re-explore or re-plan what it already answers. - If
CHANGELOG.mddoes not exist, create it using the format in section 8 before any other work. - If it exists but has no
## Current stateblock, PREPEND the block (section 8 format) above the existing content. Never rewrite, reorder, or truncate existing history.
- The
- DURING WORK: append one entry per change, in the same turn the change is
made. Never batch entries at session end. Entry format:
file:line - before->after - why - verified how - BEFORE THE SESSION ENDS (including when blocked or interrupted): rewrite
the
## Current stateblock so a fresh session with zero memory - yours or a different agent's - can continue from it alone. - Respect the DO NOT list: it records measured dead ends. Do not retry them.
2. Plan before code
For any non-trivial task (>~20 lines of change, >3 files, or any schema/ pipeline change): explore read-only first, then present a short plan and wait for approval before editing anything. The plan must contain:
- Objective (one sentence)
- Deliverable (exact file paths that will exist when done)
- Approach (key decisions + one rejected alternative if non-obvious)
- Risks/blockers (surface now, not mid-build)
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 · 206 lines · 2,408 tokens per session scan A 43bff767f8df
dev-workflow AGENTS.md is an instructions file published in the GitHub repository Dhananjay625/dev-workflow (2 stars, last pushed 20d ago), licensed MIT. It adds 2,408 tokens to every session, about $0.0120 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.
vscode buildNext.instructions.md
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
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
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.