agent-workflow-extension

A guide for changing coding-assistant workflows, agents, and reusable skills. It explains which files should contain role instructions, agent behavior, or shared workflow mechanics.

In plain words
What is it for?
Use it when editing agent definitions, reusable skills, review workflows, planning workflows, or the process for reading and replying to GitHub pull-request comments.
Why use it?
It prevents workflow rules from being placed in the wrong files and helps keep responsibilities separated when modifying an agent-based coding project.

Agent

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 agents/sflandergan/agentic-coding/agent-workflow-extension
Clone the repo
git clone --depth 1 https://github.com/sflandergan/agentic-coding
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 552 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00000 $0.00552
Opus 5 $0.00000 $0.00276
Sonnet 5 $0.00000 $0.00110
Haiku 4.5 $0.00000 $0.00055

Measured yesterday against content hash 21ec7c6da599, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agent-workflow-extension 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.

core/docs/agents/agent-workflow-extension.md · 29 lines

How it starts

The opening of the file, as written. The whole thing — 29 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent Workflow Extension Guide

Use this guide when changing coding assistant workflows, agents, or reusable skills.

Boundaries

  • docs/agents/*.md files are role loading/reference contracts. Keep them focused on which repository docs an agent must load for a workflow. Do not put detailed executable workflow behavior there.
  • .opencode/agents/*.md files define OpenCode agent behavior, permissions, default workflow, escalation rules, and tool usage.
  • .claude/skills/*/SKILL.md files define Claude skill behavior for the matching workflow.
  • .agents/skills/* files provide reusable mechanics shared by workflows. They may describe how to use bundled scripts or helpers, but they should not own role-level orchestration for review-plan, review-code, planner, implement, or finish workflows.

GitHub PR comment workflow boundary

  • The github-pr-comments skill owns reading PR comments, classifying comment target types, obtaining exact IDs, and posting approved replies through project scripts.
  • Review agents own deciding what the comments mean, validating technical claims, combining them with independent review findings, suggesting fixes, and requesting approval before edits or replies.

Default placement rules

  • If the change says what a role should do by default, update the matching .opencode/agents/*.md and .claude/skills/*/SKILL.md files.
  • If the change says which docs a role must load, update the matching docs/agents/*.md file.
  • If the change says how to run a shared helper script or avoid helper-specific mistakes, update the matching .agents/skills/* file.
  • If a workflow change affects both OpenCode and Claude, update both definitions in the same plan and verify they remain aligned.

Agent and skill references

  • OpenCode. Agents are invoked with @agentname in the task tool (e.g., @explore). A workflow agent may dispatch @explore, but should not name other workflow agents (e.g., @brainstorm, @planner) in its body — cross-workflow hand-offs are the user's responsibility.
  • Claude Code. Skills are invoked by the user with /skillname. Subagents are dispatched via the Agent tool by name with a leading @ (e.g., @explore). A workflow skill should not name other workflow skills (e.g., /brainstorm, /planner) or OpenCode agents (e.g., @implement) in its body.
  • Shared skills (under .agents/skills/) provide reusable mechanics — wrappers, scripts, methodology — and may be referenced by /name because they are not workflow orchestration.

Read the full file on GitHub · 29 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 · 29 lines · 0 tokens per session scan A 21ec7c6da599

Subscribe to this mod's changes

agent-workflow-extension is an agent published in the GitHub repository sflandergan/agentic-coding (2 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 552 tokens. 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.