feature

A guided workflow that takes a software feature from discovery and design through specification, coding, and review.

In plain words
What is it for?
It helps coordinate research, design, requirements, implementation, and final review for a new feature in a software repository.
Why use it?
It gives each stage a defined handoff and barrier, so implementation starts with enough understanding and review. It also adapts the work to the feature's scope and uncertainty.

Command

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 commands/jcarlosrodicio/opencode-agent-orchestration-kit/feature
Clone the repo
git clone --depth 1 https://github.com/jcarlosrodicio/opencode-agent-orchestration-kit
Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 699 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 $0.00016 $0.00699
Opus 5 $0.00008 $0.00349
Sonnet 5 $0.00003 $0.00140
Haiku 4.5 $0.00002 $0.00070

Measured 3d ago against content hash a34f956be14a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

feature 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 3d 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.

opencode/commands/feature.md · 72 lines

How it starts

The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Objective:

$ARGUMENTS

Run the feature flow with explicit barriers.

Routing: for free-form messages without a command, lead uses the declarative routing table in docs/ai/harness/commands.md (section "Declarative routing"). In /feature the mandatory flow below applies and takes precedence.

Init/context policy

Before the first handoff, confirm only what is needed for correct routing:

  • cwd: current repository or user-provided target directory.
  • AGENTS.md: applicable local rules when present.
  • git state: clean/dirty state if the change will touch files.
  • validation commands: likely repo checks, without running them yet unless needed to classify.
  • repo docs: local docs that are named or obvious.

Keep this policy lightweight. Small free-form work keeps the fast path; do not turn init into technical discovery.

Mandatory flow

  1. Analyze the objective only enough to classify scope, uncertainty, and handoffs; do not turn this phase into technical discovery or broad repository/config inspection.
  2. Apply the base flow: lead -> designer if applicable -> researcher -> specifier -> developer -> reviewer.
  3. Decide whether design and/or research are needed with minimal routing context. Lead's pre-handoff inspection is limited to obvious signals needed to choose the next agent.
  4. If the request states or reveals UX, brand, layout, interaction, or visual acceptance-criteria uncertainty, invoke designer before the first substantive discovery on those topics and wait for handoff.
  5. If the request states or reveals technical/product/API/library/risk/ architecture uncertainty, invoke researcher before the first substantive discovery, broad implementation/config reading, or technical conclusion by lead, then wait for output.
  6. The early handoff to researcher/designer must include the objective, detected uncertainty, constraints, and expected evidence; it must not pre-resolve the question that motivated delegation.
  7. Do not make researcher universal: if the feature is simple, clear, and has no relevant uncertainty, keep fast routing toward spec/implementation as appropriate.
  8. Parallelize designer and researcher only if their results are independent.
  9. Synthesize required design/research before invoking specifier.
  10. Invoke developer only for sufficiently specified tasks.
  11. Invoke reviewer after implementation with the task/spec, diff base, and original validation evidence. Require review_stage: final and a canonical verdict before closure.
  12. If reviewer returns needs_changes, route the blocking findings through lead back to developer, then review again. If it returns blocked, obtain the required evidence or human decision.
  13. Close with changes, validation, and risks.

Read the full file on GitHub · 72 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. 3d ago First seen · 72 lines · 16 tokens per session scan A a34f956be14a

Subscribe to this mod's changes

feature is a command published in the GitHub repository jcarlosrodicio/opencode-agent-orchestration-kit (105 stars, last pushed 5d ago), licensed Apache-2.0. It adds 16 tokens to every session and 699 once invoked, about $0.0001 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 2026-08-30.