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/sjarmak/coding-agent-workflows/agents-mdgit clone --depth 1 https://github.com/sjarmak/coding-agent-workflowsWhat 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 | $0.02636 | $0.02636 |
| Opus 5 | $0.01318 | $0.01318 |
| Sonnet 5 | $0.00527 | $0.00527 |
| Haiku 4.5 | $0.00264 | $0.00264 |
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.
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.mjsfromsource/. Do not edit this file; editsource/and re-runnpm 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)
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 · 94 lines · 2,636 tokens per session scan A b874c9b1d946
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.
Other instructions, from other repositories
ruleblast AGENTS.md
Instructions for Kpoiut/ruleblast, covering ruleblast repository instructions, evidence before confidence, change discipline and before a commit.
deep-init copilot-instructions.md
Instructions for deepfusionlabs/deep-init, covering repository instructions (copilot projection), kemal — agent context, architecture, components (7) and critical to know (non-obvious, load-bearing).
agentsmd AGENTS.md
AGENTS.md instructions for daichunghy/agentsmd, covering agents.md, setup, build, test and conventions.
agents-md AGENTS.md
Instructions for eugeniughelbur/agents-md, covering agents.md, commands, testing, project structure and code style & conventions.
ai-context-hierarchy CLAUDE.md
Instructions for CreatmanCEO/ai-context-hierarchy, covering ai-context-hierarchy — claude.md (level 1), status: active, architecture, critical rules — when editing this repo and commands.
awesome-agents-md copilot-instructions.md
Instructions for bradleybeatz1313/awesome-agents-md, covering github copilot — custom instructions for next.js 15, conventions, forbidden patterns, cache and hydration awareness and files to leave alone unless asked.