generate-roadmap

generate-roadmap is a skill for Claude Code from krokoko/cairn. It costs 51 tokens per session (1,243 once invoked), scanned A, original, Apache-2.0.

A planning tool that turns an AI-readiness assessment into a ranked list of improvements for a codebase. AI readiness here means how well a project supports reliable, increasingly independent work by coding agents.

In plain words
What is it for?
Use it to create next-step plans from a readiness report, identify blockers, compare category scores with target requirements, and plan a move to a higher AI-readiness level.
Why use it?
It shows what is missing between the project's current state and a chosen next level, so improvement work can be ordered instead of guessed.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the codebase-ai-readiness plugin — 2 skills, 1 hook 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 skills/krokoko/cairn/generate-roadmap
Any agent
npx skills add krokoko/cairn --skill generate-roadmap
Clone the repo
git clone --depth 1 https://github.com/krokoko/cairn

Made for: Claude Code.

Or install codebase-ai-readiness, the plugin that ships this one along with the rest of its 2 skills, 1 hook.

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 generate-roadmap

README.md
[![agentmods](https://agentmods.dev/badge/skills/krokoko/cairn/generate-roadmap.svg)](https://agentmods.dev/skills/krokoko/cairn/generate-roadmap)
Your own site
<a href="https://agentmods.dev/skills/krokoko/cairn/generate-roadmap"><img src="https://agentmods.dev/badge/skills/krokoko/cairn/generate-roadmap.svg" alt="Measured on agentmods" height="20"></a>
Per session 51 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,243 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 5.1 $0.00051 $0.01243
Opus 5 $0.00026 $0.00622
Sonnet 5 $0.00010 $0.00249
Haiku 4.5 $0.00005 $0.00124

Measured 6d ago against content hash 9b3a39ee0df8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

generate-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 6d 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.

plugins/codebase-ai-readiness/skills/generate-roadmap/SKILL.md · 129 lines

How it starts

The opening of the file, as written. The whole thing — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Generate AI Readiness Roadmap

Produce a detailed, prioritized improvement plan to advance the codebase to the next autonomy level (or a specified target level).

Workflow

Step 1: Load prior assessment

Search for readiness-report.md in the codebase root. If it exists, read it and extract:

  • Current overall score
  • Current autonomy level
  • Category scores
  • Existing blockers

If no report exists, inform the user: "No readiness report found. Run /assess-readiness first to generate a baseline assessment."

Also extract from the report if present: workflow artifacts summary, compound engineering score, collaboration effectiveness recommendations, alignment note (if any).

Step 2: Determine target level

  • If the user provided a target level argument (L1-L5), use that.
  • Otherwise, use the next level above the current level.
  • Load references/level-transitions.md for transition requirements.
  • If current level ≤ L2 and target level ≥ L3, load references/l2-to-l3-hinge.md and add the L2 → L3 hinge section to the roadmap.

Step 3: Identify gaps

For each category, compare the current score to what is needed for the target level. Load references/improvement-actions.md and references/improvement-actions-agent.md for common actions. Load references/implementation-phases.md for the strategic phasing model and prioritization principles.

If the report's alignment note indicates codebase ahead of practices, prioritize repo enablers from references/l2-to-l3-hinge.md and collaboration actions from improvement-actions-agent.md. If practices ahead of codebase, prioritize verification, types, CI, and testable-boundaries actions before expanding agent workflows.

Focus on:

  • Categories that are below the threshold for the target level
  • Categories with the highest weight in the scoring rubric (testable boundaries, CI reliability, machine-readable intent, structure)
  • Quick wins: actions that have high impact relative to effort
  • Sequence actions according to the 5-phase model (semantics -> fast loop -> deep evidence -> reality loop -> human repositioning)

Read the full file on GitHub · 129 lines

Files

What ships with it

6 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. 6d ago First seen · 129 lines · 51 tokens per session scan A 9b3a39ee0df8

Subscribe to this mod's changes

generate-roadmap is a skill published in the GitHub repository krokoko/cairn (14 stars, last pushed 2d ago), licensed Apache-2.0. It adds 51 tokens to every session and 1,243 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 2026-08-30.