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-statusgit 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-status)<a href="https://agentmods.dev/skills/laurigates/claude-plugins/blueprint-status"><img src="https://agentmods.dev/badge/skills/laurigates/claude-plugins/blueprint-status.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
- medium Excessive Agency · line 9 Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.
- medium Agent Snooping · line 53 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00038 | $0.04863 |
| Opus 5 | $0.00019 | $0.02431 |
| Sonnet 5 | $0.00008 | $0.00973 |
| Haiku 4.5 | $0.00004 | $0.00486 |
Grade A, and why
blueprint-status 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 3d 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 — 432 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Display the current blueprint configuration status with three-layer architecture breakdown.
When to Use This Skill
| Use this skill when... | Use blueprint-execute instead when... |
|---|---|
| You want a read-only status report (PRD/ADR/PRP counts, traceability) | You want auto-detection that takes the next action, not just reports |
| You want the three-layer architecture breakdown | Use blueprint-feature-tracker-status instead for FR/phase progress |
| You want to audit orphan docs and stale generated content | Use blueprint-sync instead for an actionable drift reconcile |
You run with --report-only for non-interactive auditing |
Use blueprint-upgrade instead when you've already spotted an upgrade |
Flags
| Flag | Description |
|---|---|
--report-only |
Display status report and exit without prompting for next action |
Steps
-
Check if blueprint is initialized:
- Look for
docs/blueprint/manifest.json - If not found, report:
Blueprint not initialized in this project. Run `/blueprint:init` to get started.
- Look for
-
Read manifest and gather information:
- Parse
manifest.jsonfor version and configuration - Parse
id_registryfor traceability metrics - Count PRDs in
docs/prds/ - Count ADRs in
docs/adrs/ - Count PRPs in
docs/prps/ - For ADRs, also count:
- With domain tags (
grep -l "^domain:" docs/adrs/*.md | wc -l) - With relationship declarations (supersedes, extends, related)
- By status (Accepted, Superseded, Deprecated)
- With domain tags (
- Count work-orders (pending, completed, archived)
- Resolve the configured rules path:
jq -r '.structure.generated_rules_path // ".claude/rules/"' docs/blueprint/manifest.json - Count generated rules in the configured path (default
.claude/rules/) - Count custom skills in
.claude/skills/ - Count custom commands in
.claude/commands/ - Check for
.claude/rules/directory - Check for
CLAUDE.mdfile - Check for
docs/blueprint/feature-tracker.json - If feature tracker exists, read statistics and last_updated
- Read
task_registryfrom manifest (if present) - For each task, calculate schedule status:
ok: Not yet due based on scheduledue: Due for execution based on scheduleoverdue: Past due by more than 1 schedule period (e.g., daily task not run in 2+ days)disabled:enabled: falsenever:last_completed_atis null (never tracked)
- Parse
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.
- 3d ago First seen · 432 lines · 38 tokens per session scan A f0027260c196
blueprint-status is a skill published in the GitHub repository laurigates/claude-plugins (58 stars, last pushed yesterday), licensed MIT. It adds 38 tokens to every session and 4,863 once invoked, about $0.0002 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.
Other skills, from other repositories
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…
things-mac
Manage Things 3 via the things CLI on macOS (add/update projects+todos via URL scheme; read/search/list from the local Things database). Use when a user asks OpenClaw to add a task to Things, list inbox/today/upcoming, search tasks, or inspect projects/areas/tags.
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.
trello
Manage Trello boards, lists, and cards via the Trello REST API.
project-setup
Initialize Claude Code framework infrastructure for any project.
ma
A coordinator for taking a software ticket from requirements through design, implementation, review, and merge request. It uses quality gates, recorded documents, approvals, and validation between stages.