pascal-mcp-sdk: Skill for Claude Code

.agents/skills/roadmap-review/SKILL.md

roadmap-review is a skill for Claude Code, Codex from frostney/pascal-mcp-sdk. It costs 43 tokens per session (654 once invoked), scanned A, a copy of roadmap-review, MIT.

A process for checking a project roadmap against current code, task-tracking records, releases, and recent delivery history. A roadmap is a plan for what a project should build and when.

In plain words
What is it for?
Use it to review roadmaps, sequence backlogs, plan releases, and identify which proposed work is actually still needed.
Why use it?
It replaces assumptions with verified evidence, measures delivery pace, and distinguishes work that is complete, partly done, or missing before planning releases.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents; installed under .agents/ (shared by several agents).

This is frostney/pascal-mcp-sdk's own configuration. It tells Claude Code and Codex how to work on pascal-mcp-sdk itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything pascal-mcp-sdk configures →

Reuse

Borrowing it

Nothing to install: this file belongs to frostney/pascal-mcp-sdk. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/frostney/pascal-mcp-sdk/main/.agents/skills/roadmap-review/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/frostney/pascal-mcp-sdk

Made for: Claude Code, Codex.

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-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/frostney/pascal-mcp-sdk/roadmap-review/github.svg)](https://agentmods.dev/skills/frostney/pascal-mcp-sdk/roadmap-review)
Your own site
<a href="https://agentmods.dev/skills/frostney/pascal-mcp-sdk/roadmap-review"><img src="https://agentmods.dev/badge/skills/frostney/pascal-mcp-sdk/roadmap-review/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for roadmap-review

Your own site · 80×15
<a href="https://agentmods.dev/skills/frostney/pascal-mcp-sdk/roadmap-review"><img src="https://agentmods.dev/badge/skills/frostney/pascal-mcp-sdk/roadmap-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 43 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 654 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 100% copy Near-identical to another mod 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 $0.00043 $0.00654
Opus 5 $0.00022 $0.00327
Sonnet 5 $0.00009 $0.00131
Haiku 4.5 $0.00004 $0.00065

Measured 8d ago against content hash c65ce0e8631e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

roadmap-review 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 8d 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.

Origin

This is a copy

100% identical to roadmap-review — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.agents/skills/roadmap-review/SKILL.md · 65 lines

How it starts

The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Roadmap review

Produce a source-verified roadmap and throughput-anchored release plan. Analysis is the deliverable; forge changes are optional and confirmation-gated.

Evidence contract

  • Pull current issues, releases, milestones, merged PR history, and project direction documents this run. Record missing sources and lower confidence rather than filling gaps from memory.
  • Measure 90-day merged-PR throughput and issue-created-to-PR-merged lead time. Use PR-opened-to-merged only as a flagged fallback. Exclude closed triage with no implementation.
  • When a domain metric exists, measure its slope from spaced historical CI artifacts. Allocation by label or area describes past effort, not capacity.
  • Before proposing or characterizing work, classify it against current code, tests, or primary specifications as Done, Partial, or Absent with evidence. Propose only Partial or Absent work.

Use a small bounded subagent fan-out only for genuinely independent, sizeable evidence areas; otherwise work directly. Synthesize before planning.

Workflow

  1. Ground the review in the evidence contract and reconcile forge counts.
  2. Assess release cadence, merged-but-unreleased work, milestone-versus-commit drift, vision, scope, and non-goals.
  3. Apply measured rates to the counted backlog, with basis and confidence. Never pad the timeline. When evidence cannot support calendar dates, report ranges and dependencies without a dated Gantt or placeholder dates.
  4. Verify every candidate against source and remove work already delivered.
  5. Plan themed releases across independent tracks, marking dependencies and the longest pole. Surface genuine human decisions with a recommendation.
  6. Stop for those decisions and present:
    • current state, drift, and release-cadence recommendation;
    • measured velocity and confidence;
    • versioned, sized tracks;
    • throughput-anchored timeline with a Mermaid Gantt when available;
    • open decisions.
  7. Offer a date-stamped ROADMAP-YYMMDD.md; do not write it without the user's request.
  8. Create or modify milestones, issues, due dates, or labels only after explicit confirmation of the finalized plan. Create each issue through /create-issue and report exactly what changed.
  9. After the confirmed milestone and its tracked scope exist, offer /milestone-rush <milestone> as an explicit next action. Never start the rush automatically; selecting it grants that skill's scoped implementation and merge authority.

Read the full file on GitHub · 65 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. 8d ago First seen · 65 lines · 43 tokens per session scan A c65ce0e8631e

Subscribe to this mod's changes

roadmap-review is a skill published in the GitHub repository frostney/pascal-mcp-sdk (2 stars, last pushed 12d ago), licensed MIT. It adds 43 tokens to every session and 654 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to roadmap-review, differing in 0 lines, and is treated as a copy.