roadmap-integration

roadmap-integration is a skill for Claude Code from marcusgoll/Spec-Flow. It costs 66 tokens per session (3,866 once invoked), scanned A, original, MIT.

A roadmap helper that manages planned product work through GitHub Issues. It checks proposed features against the project's stated vision before adding or changing them.

In plain words
What is it for?
It helps brainstorm, add, prioritize, move, search, and ship roadmap items in GitHub.
Why use it?
It keeps feature ideas organized and filters out work that does not fit the product's goals.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: reads .claude/ paths.

Good fit It helps brainstorm, add, prioritize, move, search, and ship roadmap items in GitHub.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/marcusgoll/spec-flow/roadmap-integration
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.

Any agent
npx skills add marcusgoll/Spec-Flow --skill roadmap-integration
Clone the repo
git clone --depth 1 https://github.com/marcusgoll/Spec-Flow

Made for: Claude Code.

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-integration

README.md
[![agentmods](https://agentmods.dev/badge/skills/marcusgoll/spec-flow/roadmap-integration/github.svg)](https://agentmods.dev/skills/marcusgoll/spec-flow/roadmap-integration)
Your own site
<a href="https://agentmods.dev/skills/marcusgoll/spec-flow/roadmap-integration"><img src="https://agentmods.dev/badge/skills/marcusgoll/spec-flow/roadmap-integration/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-integration

Your own site · 80×15
<a href="https://agentmods.dev/skills/marcusgoll/spec-flow/roadmap-integration"><img src="https://agentmods.dev/badge/skills/marcusgoll/spec-flow/roadmap-integration.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 66 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,866 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 $0.00066 $0.03866
Opus 5 $0.00033 $0.01933
Sonnet 5 $0.00013 $0.00773
Haiku 4.5 $0.00007 $0.00387

Measured 5d ago against content hash af168f7c0a01, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

roadmap-integration 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 5d 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.

.claude/skills/roadmap-integration/SKILL.md · 473 lines

How it starts

The opening of the file, as written. The whole thing — 473 lines — stays where its author put it; the contents beside it link to each section on GitHub.

<quick_start> <roadmap_workflow> Vision-aligned feature management:

  1. Initialize: Verify GitHub authentication (gh CLI or GITHUB_TOKEN)
  2. Load vision: Read docs/project/overview.md for alignment validation
  3. Parse intent: Identify action (add, brainstorm, move, delete, search, ship)
  4. Validate vision: Check against out-of-scope exclusions and project vision
  5. Create issue: Generate GitHub Issue with metadata (area, role, slug)
  6. Show summary: Display roadmap state and suggest next action

Quick actions:

/roadmap add "student progress widget"
/roadmap brainstorm "CFI productivity tools"
/roadmap move auth-refactor Next
/roadmap search export

Example workflow:

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
📋 VISION ALIGNMENT CHECK
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

Project Vision:
AKTR helps flight instructors track student progress against ACS standards.

Proposed Feature:
  Add student progress widget showing mastery percentage by ACS area

✅ Feature aligns with project vision

Target User Check:
Does this feature serve: CFIs, Flight students, School admins
Confirm primary user (or 'skip'): Flight students

✅ Vision alignment complete

✅ Created issue #123: student-progress-widget in Backlog
   Area: app | Role: student

📊 Roadmap Summary:
   Backlog: 12 | Next: 3 | In Progress: 2 | Shipped: 45

Top 3 in Backlog (oldest/highest priority):
1. #98 cfi-batch-export (Created: 2025-11-01)
2. #87 study-plan-generator (Created: 2025-11-05)
3. #123 student-progress-widget (Created: 2025-11-13)

💡 Next: /feature cfi-batch-export

</roadmap_workflow>

<trigger_conditions> Auto-invoke when:

  • /roadmap command executed
  • User mentions "roadmap", "add feature", "brainstorm ideas", "prioritize features"
  • Starting feature planning workflow

Prerequisites:

  • GitHub authentication (gh CLI or GITHUB_TOKEN)
  • Git repository with GitHub remote
  • Optional: docs/project/overview.md for vision validation </trigger_conditions> </quick_start>

Verify GitHub authentication and repository access.

Actions:

  • Check GitHub CLI authentication (gh auth status)
  • Fallback to GITHUB_TOKEN environment variable
  • Verify git repository has GitHub remote
  • Source roadmap manager scripts

Script location: See references/github-setup.md for platform-specific bash/powershell scripts

Validation:

AUTH_METHOD=$(check_github_auth)  # Returns: gh-cli, token, or none
REPO=$(get_repo_info)             # Returns: owner/repo-name

if [ "$AUTH_METHOD" = "none" ]; then
  echo "❌ GitHub authentication required"
  echo "Options: gh auth login OR export GITHUB_TOKEN=ghp_..."
  exit 1
fi

Output:

✅ GitHub authenticated (gh-cli)
✅ Repository: owner/repo-name

Load project vision, scope boundaries, and target users from overview.md.

When to execute:

  • Always before ADD/BRAINSTORM actions
  • Skip for MOVE/DELETE/SEARCH operations

Actions:

PROJECT_OVERVIEW="docs/project/overview.md"
HAS_PROJECT_DOCS=false

if [ -f "$PROJECT_OVERVIEW" ]; then
  HAS_PROJECT_DOCS=true
  # Extract: Vision, Out-of-Scope, Target Users
  # (see detailed extraction logic in references)
else
  echo "ℹ️  No project documentation found"
  echo "   Run /init-project to create (optional)"
fi

Extracted context:

  • Vision: 1 paragraph describing project purpose
  • Out-of-Scope: Bullet list of explicit exclusions
  • Target Users: Bullet list of intended users

See: references/vision-validation.md for extraction logic and validation rules

Read the full file on GitHub · 473 lines

Files

What ships with it

5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 5d ago First seen · 473 lines · 66 tokens per session scan A af168f7c0a01

Subscribe to this mod's changes

roadmap-integration is a skill published in the GitHub repository marcusgoll/Spec-Flow (92 stars, last pushed 4mo ago), licensed MIT. It adds 66 tokens to every session and 3,866 once invoked, about $0.0003 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.