roadmap-sync

A command that rebuilds the automatic sections of `roadmap.md` from plan files and their front matter, which is metadata at the top of a Markdown file.

In plain words
What is it for?
Use it after changing plans, statuses, or dependencies to update the Now, Next, Parallel-safe, Paused, and Linked Specs sections.
Why use it?
It keeps the roadmap aligned with plan status, dependencies, safe parallel work, and linked specifications without rewriting the rest of the document.

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/fockus/skill-memory-bank/roadmap-sync
Clone the repo
git clone --depth 1 https://github.com/fockus/skill-memory-bank
Per session 13 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 301 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 $0.00013 $0.00301
Opus 5 $0.00006 $0.00151
Sonnet 5 $0.00003 $0.00060
Haiku 4.5 $0.00001 $0.00030

Measured 2d ago against content hash 23501f09773c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

roadmap-sync 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 2d 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/roadmap-sync.md · 41 lines

What it actually says

/mb roadmap-sync

Regenerate .memory-bank/roadmap.md autosync block from plans/*.md frontmatter.

What it does

Scans .memory-bank/plans/*.md (not plans/done/) for frontmatter fields:

  • status — in_progress / queued / paused / cancelled
  • depends_on — list of plan paths
  • parallel_safe — true / false
  • linked_specs — list of spec paths

Regenerates sections between <!-- mb-roadmap-auto --> fences:

  • ## Now (in progress)
  • ## Next (strict order — depends)
  • ## Parallel-safe (can run now)
  • ## Paused / Archived
  • ## Linked Specs (active)

Content outside the fence is preserved byte-for-byte. Idempotent.

Usage

Run this command when plan frontmatter changes (status flip, new plan added, spec linked).

Under the hood it invokes scripts/mb-roadmap-sync.sh. Also runs automatically at the end of /mb plan and /mb done.

bash ~/.claude/skills/memory-bank/scripts/mb-roadmap-sync.sh

Exit codes

  • 0 — success
  • 1.memory-bank/ not found
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. 2d ago First seen · 41 lines · 13 tokens per session scan A 23501f09773c

Subscribe to this mod's changes

roadmap-sync is a command published in the GitHub repository fockus/skill-memory-bank (25 stars, last pushed 1mo ago), licensed MIT. It adds 13 tokens to every session and 301 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.