summarize-roadmap

A read-only command that turns the active backlog into a one-line-per-task roadmap, grouped by epic, or larger area of work.

In plain words
What is it for?
Checking current work by epic, seeing task totals, and producing a concise roadmap summary from a SoloFlow backlog.
Why use it?
It gives a quick view of planned work without changing task data or starting other agents. It also reports clearly when the project has not been set up or has no active tasks.

Command

Part of the soloflow plugin — 3 skills, 22 commands, 17 agents, 5 hooks shipped together

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/kesteva/soloflow/summarize-roadmap
Clone the repo
git clone --depth 1 https://github.com/kesteva/soloflow

Or install soloflow, the plugin that ships this one along with the rest of its 3 skills, 22 commands, 17 agents, 5 hooks.

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 826 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 $0.00826
Opus 5 $0.00008 $0.00413
Sonnet 5 $0.00003 $0.00165
Haiku 4.5 $0.00002 $0.00083

Measured 3d ago against content hash da666c49b217, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

summarize-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 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.

commands/summarize-roadmap.md · 68 lines

How it starts

The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/soloflow:summarize-roadmap

Print the current state of the backlog as a roadmap-style report: one line per active task, grouped by epic, with totals at the bottom. Read-only — no state mutations, no agent spawns.

Steps

  1. Check initialization. If .soloflow/ does not exist, report: "SoloFlow not initialized. Run /soloflow:init first." and stop.

  2. Fetch all active tasks. Run:

    node "${CLAUDE_PLUGIN_ROOT}/scripts/state/plan-query.js" --format json
    

    With no filters, this returns every task under .soloflow/active/plans/**/TASK-*-plan.md as a JSON array. Each element carries the task's frontmatter (id, title, status, epic, depends_on, scope_summary, plan_path).

  3. Empty-state. If the result is [], print and stop:

    ## Roadmap Summary
    
    No active tasks. Use `/soloflow:idea-extractor` or `/soloflow:roadmap` to seed the backlog.
    
  4. Group by epic. Bucket tasks by their epic frontmatter field. Treat null, missing, or empty-string as the Orphans (no epic) bucket. Sort non-orphan buckets alphabetically by slug; the orphans bucket goes last. Within each bucket, sort tasks by id ascending.

  5. Resolve epic heading. For each non-orphan slug:

    • Try Read on .soloflow/active/plans/<slug>/EPIC-<slug>.md.
    • If not found, try .soloflow/archive/done/<slug>/EPIC-<slug>.md.
    • If found, parse frontmatter and use objective as the heading text and status as the parenthetical badge.
    • If neither is found or objective is absent, fall back to the slug itself as the heading and omit the status badge.
  6. Format the report. Per-task line:

    - [<status>] TASK-NNN — <title>
    

    The task's title field is the one-sentence summary. Use raw status values (ready, deferred, pending, in_progress, blocked, stuck, human_needed).

    Add an indented ↳ blocked by: TASK-A, TASK-B line only when the task's status is blocked AND depends_on is a non-empty list.

Read the full file on GitHub · 68 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 · 68 lines · 16 tokens per session scan A da666c49b217

Subscribe to this mod's changes

summarize-roadmap is a command published in the GitHub repository kesteva/soloflow (40 stars, last pushed 3mo ago), licensed MIT. It adds 16 tokens to every session and 826 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.