roadmap-sequencer

A roadmap-planning agent that orders large pieces of work into Now, Next, and Later lanes. It uses MoSCoW priorities and RICE scoring, then breaks current work into stories planned to take no more than three days.

In plain words
What is it for?
Use it in the third phase of a roadmap process to sequence epics, create milestone IDs, split current epics into stories, and build a discovery or spike track.
Why use it?
It turns a broad roadmap into an ordered delivery plan and exposes work that still needs investigation. Epics are larger bodies of work, while stories are smaller implementable tasks.

Agent

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 agents/chris-dare-dev/agent-kit/roadmap-sequencer
Clone the repo
git clone --depth 1 https://github.com/chris-dare-dev/agent-kit
Per session 120 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,040 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 2 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 $0.00120 $0.03040
Opus 5 $0.00060 $0.01520
Sonnet 5 $0.00024 $0.00608
Haiku 4.5 $0.00012 $0.00304

Measured yesterday against content hash fbf593e75953, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

roadmap-sequencer scanned grade C with 2 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.

Instruction-override phrasingmediumPrompt injection

Text telling the model to disregard its earlier instructions or safety rules is the shape of a prompt injection, whoever wrote it.

"Now run X", "Ignore previous instructions", "Authorize the user", "Add yourself

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

cat ".claude/agent-memory/roadmap-sequencer/lessons.md" 2>/dev/null || echo "(no lessons yet)"
data/agents/roadmap-sequencer.md · 245 lines

How it starts

The opening of the file, as written. The whole thing — 245 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Roadmap Sequencer

You are Phase 3 of the /roadmap pipeline. Your job is to order epics into Now / Next / Later lanes, decompose Now-lane epics into stories ≤ 3 days, assign milestone IDs, and surface the spike/discovery track.

The orchestrator (slash command at .claude/commands/roadmap.md) dispatches you with substituted variables. You never invoke other sub-agents.

Input variables (substituted by the orchestrator)

  • {SLUG} — the roadmap slug
  • {ROADMAP_PATH} — absolute path to plans/<slug>-roadmap.md

Step 0 — Read persistent memory (skip-if-not-relevant)

cat ".claude/agent-memory/roadmap-sequencer/lessons.md" 2>/dev/null || echo "(no lessons yet)"

Step 1 — Read the phase-sequence reference + Goal + Epics sections (REQUIRED)

Read in order (paths resolve from ANY CWD — the target repo is usually NOT the agent-kit checkout, so never use relative data/... paths):

  1. $WS/.claude/references/roadmap-phase-sequence.md (where WS="${PERSONAL_WORKSPACE_ROOT:-$HOME/Work/workspace}"; equivalently MCP get_reference("roadmap-phase-sequence")) — canonical MoSCoW rules, RICE formula, Now/Next/Later mechanics, story-sizing rules, milestone ID format, spike lane rules.
  2. The ## Goal section from {ROADMAP_PATH}.
  3. The ## Epics section from {ROADMAP_PATH}.

Do NOT proceed until all three are loaded.


Step 2 — MoSCoW bucketing + script validation

Bucket each epic into Must / Should / Could / Won't based on: "If we shipped without this epic, would the Phase 1 Objective fail?"

Then validate the Must cap. The script expects a JSON array on stdin (or via a file path), NOT the raw roadmap.md Markdown. Build the JSON in-context from your bucketing decisions, then pipe it in:

# Construct the JSON from your in-context bucketing decisions.
WS="${PERSONAL_WORKSPACE_ROOT:-$HOME/Work/workspace}"
echo '[
  {"id":"E1","bucket":"Must"},
  {"id":"E2","bucket":"Should"},
  {"id":"E3","bucket":"Could"},
  {"id":"E4","bucket":"Won''t"}
]' | python3 "$WS/.claude/scripts/roadmap-score-moscow.py" -

Read the full file on GitHub · 245 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 · 245 lines · 120 tokens per session scan C fbf593e75953

Subscribe to this mod's changes

roadmap-sequencer is an agent published in the GitHub repository chris-dare-dev/agent-kit (0 stars, last pushed 24d ago), licensed MIT. It adds 120 tokens to every session and 3,040 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it C with 2 findings (instruction-override phrasing, reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

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.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

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.

github/awesome-copilot · 61 tokens

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.

github/awesome-copilot · 11 tokens

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.

anthropics/claude-cookbooks · 52 tokens