roadmap-drift-watcher

roadmap-drift-watcher is an agent for Claude Code from daddia/claude-for-strategy. It costs 36 tokens per session (557 once invoked), scanned A, original, MIT.

A scheduled monitoring agent that checks whether transformation initiatives have moved into their planned roadmap phases.

In plain words
What is it for?
It is for weekly roadmap tracking and reporting phase changes and their downstream effects.
Why use it?
It identifies work that is late, blocked, moved backwards, or likely to disrupt dependent initiatives.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter.

Part of the transformation plugin — 5 skills, 3 agents shipped together

Good fit It is for weekly roadmap tracking and reporting phase changes and their…

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/daddia/claude-for-strategy/roadmap-drift-watcher
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.

Clone the repo
git clone --depth 1 https://github.com/daddia/claude-for-strategy

Made for: Claude Code.

Or install transformation, the plugin that ships this one along with the rest of its 5 skills, 3 agents.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for roadmap-drift-watcher

README.md
[![agentmods](https://agentmods.dev/badge/agents/daddia/claude-for-strategy/roadmap-drift-watcher.svg)](https://agentmods.dev/agents/daddia/claude-for-strategy/roadmap-drift-watcher)
Your own site
<a href="https://agentmods.dev/agents/daddia/claude-for-strategy/roadmap-drift-watcher"><img src="https://agentmods.dev/badge/agents/daddia/claude-for-strategy/roadmap-drift-watcher.svg" alt="Measured on agentmods" height="20"></a>
Per session 36 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 557 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00036 $0.00557
Opus 5 $0.00018 $0.00279
Sonnet 5 $0.00007 $0.00111
Haiku 4.5 $0.00004 $0.00056

Measured 3d ago against content hash d85347336a6d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

roadmap-drift-watcher 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.

transformation/agents/roadmap-drift-watcher.md · 38 lines

How it starts

The opening of the file, as written. The whole thing — 38 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Roadmap-Drift Watcher

Runs weekly by default (Thursday 09:00) — override the schedule to match the planning-check cadence recorded in the practice profile if it differs.

What it does

  1. Reads the practice profile for the default roadmap track model, planning-horizon convention (what Now / Next / Later or named tracks mean in calendar terms), and seed-document locations.

  2. Gets the current roadmap and progress signals — the latest roadmap-builder output, any updated initiative status in seed documents or the workspace, and (if the PMO plugin is installed) milestone actuals from wherever the PMO profile points. Do not infer phase placement from partial information.

  3. Compares each initiative's actual phase or progress against its planned phase — an initiative is drifting when it should have advanced per the planning horizon but has not, or when it has slipped backward (de-scoped, re-baselined to a later track, or blocked long enough that the original phase assignment no longer holds).

  4. For every drifting initiative, states the knock-on effect — which dependent initiatives are now blocked or mis-sequenced, which phase is overloaded or under-delivering relative to capacity flags, and whether the overall ambition timeline is threatened. Do not stop at "Initiative X is still in Now" — say what downstream work cannot start or what commitment is now at risk.

  5. Cross-checks dependencies from the roadmap's DEPENDENCIES section — a slipped initiative often matters because something in the next phase was waiting on it.

  6. Posts the summary to ~~chat. If no chat connector is configured, write the summary to a file in the workspace instead.

  7. Includes an all-clear footer when no initiatives are slipping their phase. The footer means the agent ran — initiatives on track within the planning horizon may still have local delays that do not constitute phase drift.

Trust spine

When citing dates, costs, or progress figures from scanned artifacts, preserve existing sourcing tags. Do not invent completion percentages or slip days — flag what is evidenced vs. what needs a human update.

Read the full file on GitHub · 38 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 · 38 lines · 36 tokens per session scan A d85347336a6d

Subscribe to this mod's changes

roadmap-drift-watcher is an agent published in the GitHub repository daddia/claude-for-strategy (2 stars, last pushed 2mo ago), licensed MIT. It adds 36 tokens to every session and 557 once invoked, about $0.0002 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 2026-09-03.