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.
npx skills add krokoko/cairn --skill generate-roadmapgit clone --depth 1 https://github.com/krokoko/cairnWrote 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.
[](https://agentmods.dev/skills/krokoko/cairn/generate-roadmap)<a href="https://agentmods.dev/skills/krokoko/cairn/generate-roadmap"><img src="https://agentmods.dev/badge/skills/krokoko/cairn/generate-roadmap/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.
<a href="https://agentmods.dev/skills/krokoko/cairn/generate-roadmap"><img src="https://agentmods.dev/badge/skills/krokoko/cairn/generate-roadmap.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00071 | $0.01236 |
| Opus 5.5 | $0.00028 | $0.00494 |
| Sonnet 5.5 | $0.00014 | $0.00247 |
| Haiku 4.5 | $0.00007 | $0.00124 |
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 16d 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.
How it starts
The opening of the file, as written. The whole thing — 128 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.mdfor transition requirements. - If current level ≤ L2 and target level ≥ L3, load
references/l2-to-l3-hinge.mdand 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)
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.
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.
- 16d ago Changed · -1 lines · +20 tokens per session d394fc64f659
- 1mo ago First seen · 129 lines · 51 tokens per session scan A 9b3a39ee0df8
generate-roadmap is a skill published in the GitHub repository krokoko/cairn (18 stars, last pushed 14d ago), licensed Apache-2.0. It adds 71 tokens to every session and 1,236 once invoked, about $0.0003 per session on Opus 5.5. 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.
Other skills, from other repositories
civic-publish-gate
Run deterministic source, citation, freshness, privacy, meeting-certainty, accessibility, correction-state, and human-approval checks before civic publication.
civic-newsroom-plan
Plan an evidence-bound civic newsroom workflow with provenance, privacy, citation, correction, accessibility, and human publication gates.
editorial-correction-review
Review a challenged civic claim and prepare a visible, append-only correction or withdrawal with downstream propagation evidence.
local-resource-index
Index cited local emergency, transit, and human-service resources with authority, freshness, correction, and takedown controls.
install-nightshift
Install the full Nightshift plugin, with its hooks and runtime, into Claude Code, Codex or Cursor.
goal-writer
Drafts a goal+rider document pair that briefs an autonomous coding agent on one round of work — a goal file under 4,000 characters (sized to fit the /goal command in both Claude Code and Codex) plus an unbounded rider with phased plans and named depth tests. Use when the user says "draft a goal", "write a goal+rider"…