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.
git clone --depth 1 https://github.com/chriswritescode-dev/opencode-forgeWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/chriswritescode-dev/opencode-forge/goal)<a href="https://agentmods.dev/commands/chriswritescode-dev/opencode-forge/goal"><img src="https://agentmods.dev/badge/commands/chriswritescode-dev/opencode-forge/goal/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/chriswritescode-dev/opencode-forge/goal"><img src="https://agentmods.dev/badge/commands/chriswritescode-dev/opencode-forge/goal.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00000 | $0.00669 |
| Opus 5.5 | $0.00000 | $0.00268 |
| Sonnet 5.5 | $0.00000 | $0.00134 |
| Haiku 4.5 | $0.00000 | $0.00067 |
Grade A, and why
goal 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 7d 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.
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 — 39 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plan a multi-chunk goal. Resolve its tasks, save the ordered goal, then plan chunk 1 so the user can launch it as a loop.
Input: $ARGUMENTS
Step 1: Objective
The objective is the input above. If it is empty, ask the user for the objective and stop until they provide one.
Step 2: Resolve the work
If the objective refers to tickets, issues, or tasks in a tracker (GitHub issues, Linear, Jira, or similar), or to a selection such as "tasks 1-10" or "all remaining tickets", list and read them with the tools already available in this session (for example gh issue list / gh issue view, or the tracker's MCP tools). This is strictly read-only: never comment on, assign, label, transition, close, or otherwise modify a ticket. If the tracker cannot be reached with the available tools, ask the user for the task details instead of guessing.
For an objective with no tracker, break it into an ordered list of large, coherent chunks of work.
Step 3: Settle the route
The objective is the fixed outcome. Research the repository against the objective and resolved tasks, then settle the route with grouped question rounds exactly as your planning workflow's Narrow step describes, until every route decision is settled — especially decisions that span chunks, such as shared owners, data and interface shapes, conventions, and task boundaries. Later chunks are planned without you, so every route decision they depend on must be decided now. These rounds also cover chunk 1; in Step 6 ask another round only for a route decision specific to chunk 1 that this step did not settle.
Step 4: Order the tasks
Order the tasks for execution, dependencies first. Each task becomes its own chunk (one loop per task). Combine two tickets into one task only when they cannot be implemented separately, and list both refs in that task.
Step 5: Save the goal
Call goal-write with:
title: a short title for the goal.objective: the objective verbatim, followed by aRoute decisions:list of every route decision settled in Step 3.tasks: the ordered list. For each task setrefto the ticket identifier when one exists,title, anddetailsto a self-contained summary of the task including its acceptance criteria and the route decisions that apply to that task.
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.
- 7d ago First seen · 39 lines · 0 tokens per session scan A 3ac7709a0d2c
goal is a command published in the GitHub repository chriswritescode-dev/opencode-forge (13 stars, last pushed 6d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 669 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 2026-10-19.
Other commands, from other repositories
template
Manage issue templates for streamlined issue creation.
fest-show
Show festival progression (in-progress tasks, roadmap, and dependency view).
add-note
Add an internal or external note to a ConnectWise PSA ticket.
sync-linear
Sync current work with Linear ticket status.
dispatcher
Use when you want the orchestrator to pick the next repo to work on across your whole portfolio — it enumerates candidate repos below the confinement root, resolves free/busy from each repo's session.lock lease, ranks the FREE ones by backlog priority × staleness × readiness, recommends the single most worthwhile one…
workpm
A project-management workflow for coordinating multiple AI workers through five stages. It includes task assignment, shared activity logs, worker replacement, and final checks.