roadmap

A release roadmap is a plan showing which product features will be delivered in each phase of a release. This command builds or updates one from a product requirements document and supporting analysis.

In plain words
What is it for?
Use it to plan releases such as an MVP or version 1.0, group features into phases, and prioritise work using requirements, analysis, project principles, and existing feature specifications.
Why use it?
It turns a list of ideas and research findings into an ordered delivery plan. It also helps decide what belongs in each phase and what should wait.

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/skullninja/coco-workflow/roadmap
Clone the repo
git clone --depth 1 https://github.com/skullninja/coco-workflow
Per session 29 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,040 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 $0.00029 $0.02040
Opus 5 $0.00015 $0.01020
Sonnet 5 $0.00006 $0.00408
Haiku 4.5 $0.00003 $0.00204

Measured yesterday against content hash 4c67bfed7813, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

roadmap 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.

commands/roadmap.md · 225 lines

How it starts

The opening of the file, as written. The whole thing — 225 lines — stays where its author put it; the contents beside it link to each section on GitHub.

User Input

$ARGUMENTS

Setup

  1. Read .coco/config.yaml for:
    • discovery.prd_path (default: docs/prd.md)
    • discovery.analysis_dir (default: docs/analysis)
    • discovery.roadmap_dir (default: docs/roadmap)
    • project.specs_dir (default: specs)
    • issue_tracker.provider
  2. $ARGUMENTS specifies the release name (e.g., "v1.0", "MVP"). If empty, use AskUserQuestion to ask for the release name.
  3. Check if a roadmap already exists at {roadmap_dir}/{release}.md:
    • If yes, enter update mode (load existing roadmap)
    • If no, enter create mode

Execution

1. Load Context

PRD (required): Read {discovery.prd_path}. If the file does not exist, ERROR: "No PRD found at {discovery.prd_path}. Run /coco:prd first."

Analysis docs (optional): Glob {discovery.analysis_dir}/*.md and read all found documents. Extract:

  • Key findings from each
  • "Implications for Roadmap" sections

Constitution (optional): Read .coco/memory/constitution.md if it exists. Use project principles to inform prioritization.

Existing specs (optional): Glob {specs_dir}/*/design.md (with {specs_dir}/*/spec.md as legacy fallback). These represent features already designed -- they should appear in the roadmap as already-scoped items.

Existing roadmap (update mode only): Load {roadmap_dir}/{release}.md. Preserve Change Log and completed feature statuses.

2. Extract Feature Candidates

Build a consolidated feature list from all sources:

Source How
PRD "Feature Candidates" table Parse rows: name, description, goal(s), priority
Analysis "Implications for Roadmap" sections Extract referenced features and adjustments
Existing specs/ directories Add as already-specced features

Deduplicate by name/description similarity. Output the consolidated list as text (do NOT put it inside AskUserQuestion — it must be visible before the prompt):

Feature Candidates for {release}
================================
| # | Feature | Source | Already Specced | Notes |
|---|---------|--------|-----------------|-------|

Read the full file on GitHub · 225 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 · 225 lines · 0 tokens per session scan A 4c67bfed7813

Subscribe to this mod's changes

roadmap is a command published in the GitHub repository skullninja/coco-workflow (7 stars, last pushed yesterday), licensed MIT. It adds 29 tokens to every session and 2,040 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 2026-08-31.