Feature track
Takes a feature from open questions to a reviewed implementation in six gated steps, saving each step's artifact to the repo. Use for any change bigger than a quick fix.
Builds the feature "" in small, reviewable steps. Each step writes one artifact and stops for approval before the next one starts, so the human stays in control of scope and design while the agent does the legwork. Later steps read the earlier artifacts instead of re-asking.
Step 1: Questions
Read the request for "" and the code it touches. Write the questions whose answers would change the design: users, edge cases, constraints, non-goals and how success is measured. Group them, keep each one answerable in a sentence, and mark the ones you can answer yourself from the code (with the answer).
Stop and wait for the answers.
Step 2: Research
Using the answered questions, map the current system: the files, modules, data and external services involved, and how a request flows through them today. Note existing patterns the feature should follow and anything that will make it harder. Cite file paths. Do not propose a design yet.
Stop and wait for approval.
Step 3: Design
Propose the design for "": the approach, the alternatives you rejected and why, data and API changes, failure modes, and how it will be tested. Keep it to what a reviewer needs to say yes or no.
Stop and wait for approval.
Step 4: Structure
List every file to add or change, with a one-line purpose each, plus new types, functions and their signatures. Flag anything that touches a shared or public interface.
Stop and wait for approval.
Step 5: Plan
Turn the approved design and structure into an ordered list of small steps. Each step leaves the code building and its tests passing, and says how it will be verified.
Stop and wait for approval.
Step 6: Implement
Carry out the plan one step at a time. After each step, run its verification and report the real result. If reality differs from the plan, stop and say how before continuing. Finish with what changed, what was verified, and anything left open.
1 required value still a placeholder; the assistant will ask for it.
details
- kind
- Workflow: ordered steps with a checkpoint between them
- domain
- Software engineering
- category
- Planning
- needs
- repo-read, file-write
- risk
- edits-files
- version
- v1.0.0 · incubating
- works in
- Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Antigravity, OpenCode, Windsurf, Zed, Continue, AGENTS.md
use in
npx @hermes-hq/hodios install feature-track --target claude-codenpx skills add hermes-hq/hodios-dist --skill feature-track -a claude-codeclaude plugin marketplace add hermes-hq/hodios-distclaude plugin install hodios-software-engineering@hodiosThe plugin brings every entry in this domain at once.
more in planning
All of PlanningBreak down an epic
Splits an epic into small, ordered vertical slices that each deliver testable value, with acceptance checks, dependencies and spikes. Use when an epic or large feature is too big to start.
break-down-epicEstimate work as a range
Breaks engineering work into tasks and produces a range estimate with a confidence level, stated assumptions and the unknowns that need a spike. Use when asked "how long will this take?".
estimate-with-rangesPlan a spike
Turns a technical unknown into a time-boxed spike with a sharp question, exit criteria, cheapest-first experiments and a clear deliverable. Use when an unknown blocks a decision or an estimate.
plan-spikeWrite an implementation plan
Reads the codebase and writes an ordered implementation plan in small verifiable steps, with files to touch, tests, rollout and risks. Use before coding any change that spans several files.
write-implementation-planPlan a sprint
Builds a sprint plan from a backlog and real capacity, with a sprint goal, committed and stretch items, dependencies, risks and what it deliberately leaves out. Use before sprint planning.
plan-sprintTriage an issue backlog
Triages a batch of issues for maintainers with duplicates, labels, severity, needs-info replies and what to close. Use when the tracker grows faster than the team can read it.
triage-issue-backlog