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 laurigates/claude-plugins --skill blueprint-upgradegit clone --depth 1 https://github.com/laurigates/claude-pluginsWrote 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/laurigates/claude-plugins/blueprint-upgrade)<a href="https://agentmods.dev/skills/laurigates/claude-plugins/blueprint-upgrade"><img src="https://agentmods.dev/badge/skills/laurigates/claude-plugins/blueprint-upgrade/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/laurigates/claude-plugins/blueprint-upgrade"><img src="https://agentmods.dev/badge/skills/laurigates/claude-plugins/blueprint-upgrade.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00033 | $0.02783 |
| Opus 5.5 | $0.00013 | $0.01113 |
| Sonnet 5.5 | $0.00007 | $0.00557 |
| Haiku 4.5 | $0.00003 | $0.00278 |
Grade A, and why
blueprint-upgrade 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 4d 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 — 191 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Upgrade the blueprint structure to the latest format version.
When to Use This Skill
| Use this skill when... | Use blueprint-init instead when... |
|---|---|
| The project has a manifest at v1.x, v2.x, v3.0, v3.1, or v3.2 | The project has no docs/blueprint/manifest.json at all |
| You want the user-facing upgrade entry point with prompts | Use blueprint-migration instead when implementing version-specific logic |
| You're adding the v3.2 task registry or v3.3 monorepo workspaces | Use blueprint-execute instead when you want auto-detection of next step |
You're running batch upgrades across repos with --non-interactive/-y |
Use blueprint-status instead to first audit current version |
Current Format Version: 3.4.0
This command delegates version-specific migration logic to the blueprint-migration skill.
Parameters
Parse $ARGUMENTS for flags before running any step:
--non-interactive,--yes,-y: Skip everyAskUserQuestionprompt and apply the defaults in the table below. Intended for batch runs across many repos.
Set an internal $NONINTERACTIVE flag to true when any of those tokens appear in $ARGUMENTS; otherwise false. Reference this flag at every AskUserQuestion call site in the steps below.
Non-interactive defaults
When $NONINTERACTIVE is true, use these answers without prompting and record them in upgrade_history[].changes as "auto-selected in non-interactive mode":
| Decision point | Step | Default | Rationale |
|---|---|---|---|
| Remove deprecated generated commands | 3 | "Yes, remove" | Matches "Recommended" option; the files are known-obsolete |
| Task-registry scheduling mode | 3a | "Prompt before running" | Safest; preserves pre-existing behaviour for all tasks |
| Upgrade confirmation | 5 | "Yes, upgrade now" | The flag is explicit consent; skip the confirmation gate |
| Enable document detection (v1.x→v2.0) | 7f | "No, keep manual commands only" | Additive feature; do not silently change behaviour in batch mode |
| Migrate root documentation (v1.x→v2.0) | 7g | "No, leave in root" | Least destructive; moving root docs is reversible but surprising |
| Post-upgrade next action | 11 | Skip — report and exit | The caller is responsible for follow-up in a batch context |
What ships with it
9 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.
- REFERENCE.md 2.3 KB
- references/deprecated-commands.md 1.7 KB
- references/next-action-prompt.md 625 B
- references/upgrade-plan.md 1.4 KB
- references/v1.x-to-v2.0-overview.md 2.9 KB
- references/v2.x-to-v3.0-overview.md 3.1 KB
- references/v3.1-to-v3.2-task-registry.md 1.7 KB
- references/v3.2-to-v3.3-summary.md 770 B
- references/v3.3-to-v3.4-summary.md 813 B
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.
- 4d ago Changed · +9 lines 9c4f8d83b785
- 9d ago Changed · -283 lines scan D → A 3befadf95afd
- 1mo ago First seen · 465 lines · 33 tokens per session scan D 8e9be99d9f49
blueprint-upgrade is a skill published in the GitHub repository laurigates/claude-plugins (60 stars, last pushed yesterday), licensed MIT. It adds 33 tokens to every session and 2,783 once invoked, about $0.0001 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 2026-09-03.
Other skills, from other repositories
morning-brief
Operator's read-only morning view of the current GitHub repo in one pass: open counts per queue label, merge-ready PRs, parked decisions with their RECOMMENDED lines, and loop-lane telemetry freshness; never mutates issues, PRs, labels, or comments. Use when: 'morning brief', 'ops dashboard', 'what needs attention'…
sdlc
Run an artifact-driven software lifecycle where each stage commits a markdown artifact that triggers the next - intent.md, spec.md, plan.md, verified diff, reviewed PR, monitored production. Use when the user asks to capture an idea as intent, write a spec, plan before implementing, set up a verification loop, define…
podio-ticket-updates
Sync in-progress Podio Kanban tickets with progress from their linked GitHub repos — propose description updates and progress comments, apply after approval. Use when the user asks to update Podio tickets, sync ticket progress, or post status updates to the Kanban board.
parallel-orchestrator
Manage parallel Claude Code workstreams using git worktrees. Use when: splitting large tasks across multiple workers, coordinating parallel development, monitoring worker progress, integrating completed work, analyzing work item documents (code reviews, issue lists). Triggers: parallel, orchestrator, worktrees…
tracker-writing
Write Jira issues, Jira comments, and GitHub pull request titles and bodies for the openEHR specification trackers and repos. Use whenever text is about to be posted to Jira or GitHub: create or edit an issue, comment, open a PR, write a review comment. Hard length caps, a fixed structure per text type, ask before…
kanban-dev-lane
Use when a Hermes Kanban worker wants to run an autonomous implementation delegation lane with a 3-tier fallback chain across claudy -> codex (--yolo) -> agyd (agy --dangerously-skip-permissions) -> Hermes direct on quota exhaustion.