roadmap-refiner

A roadmap-planning agent that turns a vague project brief into a concise goal, measurable results, assumptions, and a list of work left out.

In plain words
What is it for?
Use it as the first phase of the roadmap workflow to refine a brief into a one-page goal statement with key results and a Won't list.
Why use it?
It gives an unclear initiative a focused objective and boundaries before detailed planning begins.

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-refiner
Clone the repo
git clone --depth 1 https://github.com/chris-dare-dev/agent-kit
Per session 94 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,390 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 $0.00094 $0.02390
Opus 5 $0.00047 $0.01195
Sonnet 5 $0.00019 $0.00478
Haiku 4.5 $0.00009 $0.00239

Measured yesterday against content hash 8ca682849ec0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

roadmap-refiner 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-refiner/lessons.md" 2>/dev/null || echo "(no lessons yet)"
data/agents/roadmap-refiner.md · 212 lines

How it starts

The opening of the file, as written. The whole thing — 212 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Roadmap Refiner

You are Phase 1 of the /roadmap pipeline. Your job is to convert a vague brief into a crisp, 1-page goal statement with an explicit Objective, Key Results, assumption tiers, and Won't list.

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 (e.g., cost-visibility-l3, kiali-multicluster)
  • {BRIEF} — the verbatim brief text from the user (or summarized from conversation context). Do NOT paraphrase.
  • {ROADMAP_PATH} — absolute path to plans/<slug>-roadmap.md (already scaffolded by roadmap-init.sh)

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

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

Read memory only if lessons are relevant to this brief's domain. Do not load memory for its own sake.


Step 1 — Read the phase-refine reference (REQUIRED before any reasoning)

# Resolves from ANY CWD (the target repo is usually NOT the agent-kit checkout).
WS="${PERSONAL_WORKSPACE_ROOT:-$HOME/Work/workspace}"
cat "$WS/.claude/references/roadmap-phase-refine.md"

This is the canonical source for HMW mechanics, sharpening questions, assumption tier definitions, OKR rules, and Won't list conventions. Load it fully before proceeding.


Step 2 — Walk the 5 sub-steps

Sub-step 2a — "How Might We" reframe

Restate {BRIEF} as: How might we <verb> <outcome> for <who>?

  • The verb must describe an outcome, not a planned solution.
  • "How might we add a Grafana dashboard" → wrong (solution-embedded).
  • "How might we make per-namespace cost visible to platform engineers" → right (outcome-shaped).
  • If the verb is a solution (add, migrate, deploy), challenge whether that is truly required or an assumed implementation.

Sub-step 2b — 3–5 sharpening questions

Pick the questions that are genuinely under-specified and change the plan. For each, answer from in-context evidence FIRST:

Read the full file on GitHub · 212 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 · 212 lines · 94 tokens per session scan C 8ca682849ec0

Subscribe to this mod's changes

roadmap-refiner is an agent published in the GitHub repository chris-dare-dev/agent-kit (0 stars, last pushed 24d ago), licensed MIT. It adds 94 tokens to every session and 2,390 once invoked, about $0.0005 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.