coding-agent-workflows AGENTS.md

An index of coding-agent instructions for the sjarmak/coding-agent-workflows project. It points agents to fuller guidance on collaboration, architecture, coding style, databases, and development workflows.

In plain words
What is it for?
Use it when an agent needs project rules or workflow guidance. The full details are stored in AGENTS.full.md and are organized into named sections.
Why use it?
It gives coding agents a shared set of project practices without putting all of the guidance directly into the short AGENTS.md file.

Instructions file for CodexOpenCode

Install

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.

agentmods
npx agentmods add instructions/sjarmak/coding-agent-workflows/agents-md
Clone the repo
git clone --depth 1 https://github.com/sjarmak/coding-agent-workflows

Made for: Codex, OpenCode.

Per session 2,636 This file is loaded in full into every session.
When invoked 2,636 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.02636 $0.02636
Opus 5 $0.01318 $0.01318
Sonnet 5 $0.00527 $0.00527
Haiku 4.5 $0.00264 $0.00264

Measured yesterday against content hash b874c9b1d946, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

coding-agent-workflows 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.

AGENTS.md · 94 lines

How it starts

The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agentic Coding Practices

Generated by build/render.mjs from source/. Do not edit this file; edit source/ and re-run npm run build.

Coding standards, agent roles, skills, and workflows that read the same across coding agents. This file is an index: each entry below is a pointer, not the content. The full text lives in AGENTS.full.md next to this file — read the named section there when a task needs it, and only that section.

Principles

Each is a section (matched by heading) in AGENTS.full.md:

  • Agent Collaboration (common/agent-collaboration.md)
  • Agent Orchestration (common/agents.md)
  • Anti-Slop & Code Erosion (common/anti-slop.md)
  • Architecture Principles (common/architecture.md)
  • Augmented Coding Patterns (common/augmented-coding-patterns.md)
  • Code Knowledge Graphs (common/code-graph.md)
  • Coding Style (common/coding-style.md)
  • Context Layering (common/context-layering.md) — The four context layers an agent reads, and the one-fact-one-layer rule that keeps AGENTS.md thin and free of conflict with memory.
  • Database & SQL (common/database.md)
  • Development Workflow (common/development-workflow.md)
  • Git Workflow (common/git-workflow.md)
  • House Rules (always-on) (common/house-rules.md) — Always-on essentials — autonomy boundary, output discipline, coding/architecture/security standards, ZFC, anti-slop trigger. Detailed catalogs are in rules/reference/ (on-demand).
  • Common Patterns (common/patterns.md)
  • Performance Optimization (common/performance.md)
  • Security Guidelines (common/security.md)
  • Skill Management (common/skill-management.md) — Discover, vet, and expose agent skills on demand with skillager, so the right skills are available per task without loading every skill into every chat.
  • Task Management (common/task-management.md) — Track multi-step agent work in a durable, dependency-aware task store; prefer the lightest non-invasive backend (SQLite + JSONL) and only add heavier sync when you actually need it.
  • Testing Requirements (common/testing.md)

Read the full file on GitHub · 94 lines

Changes

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.

  1. yesterday First seen · 94 lines · 2,636 tokens per session scan A b874c9b1d946

Subscribe to this mod's changes

coding-agent-workflows AGENTS.md is an instructions file published in the GitHub repository sjarmak/coding-agent-workflows (2 stars, last pushed 1mo ago), licensed MIT. It adds 2,636 tokens to every session, about $0.0132 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.