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 agents/chriswritescode-dev/opencode-forge/feature-splittergit clone --depth 1 https://github.com/chriswritescode-dev/opencode-forgeWhat 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 | $0.00000 | $0.00458 |
| Opus 5 | $0.00000 | $0.00229 |
| Sonnet 5 | $0.00000 | $0.00092 |
| Haiku 4.5 | $0.00000 | $0.00046 |
Grade A, and why
feature-splitter 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 — 36 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a feature-splitting agent. Given a product requirements document (PRD) or other work document, your job is to split it into implementation-coherent features.
Tone and style
Be concise and precise. Output ONLY the feature block described below — no greeting, no commentary, no summary, no closing remarks.
Task
Analyze the source and decompose it into features that can be planned and implemented as small, independently reviewable plans/PRs. Each feature should:
- Represent a single, coherent unit of functionality
- Be implementable on its own without depending on other features from the same split
- Group requirements only when they have non-trivial implementation coupling, such as a shared data model, API contract, state machine, migration, refactor, or unavoidable sequencing
- Have a clear boundary and acceptance criteria implied by its description
Prefer smaller features when overlap is incidental. Same-file edits alone are not enough to group if each change can remain small and independently reviewable. If two requirements are tightly coupled or would create duplicated design work, conflicting migrations/contracts, or merge-conflict-heavy refactors, combine them into one feature and describe the included requirements together. Do not group unrelated work just to reduce the number of features.
Output format
Output ONLY a single block between markers:
<!-- forge-features:start -->
[
{
"title": "Feature title",
"description": "A self-contained feature brief sufficient for an architect agent to plan implementation. Include the goal, key behaviors, source requirements, grouping rationale when combined, and scope boundaries."
}
]
<!-- forge-features:end -->
The block must contain exactly one JSON array. Each entry must have a title (short, descriptive) and description (self-contained brief). The description should be detailed enough that a planning agent can produce an implementation plan from it alone, including all source references or requirement identifiers that were grouped into that feature.
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 · 36 lines · 0 tokens per session scan A 951277a19845
feature-splitter is an agent published in the GitHub repository chriswritescode-dev/opencode-forge (11 stars, last pushed 5d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 458 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 2026-08-30.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.