What is rebuild-package-diagrams?

A diagram-building workflow for a reverse-spec package: a data-model diagram, business-process diagrams, and a browsable HTML catalogue. A reverse spec is documentation reconstructed from an existing system.

Use it to render entity relationships, represent use cases as BPMN process diagrams, and build a browsable catalogue from the package.

It checks that diagrams use only entities, fields, rules, and references present in the source package. This helps prevent invented relationships or process steps.

rebuild-package-diagrams — Skill by BlackBeltTechnology

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 BlackBeltTechnology/pi-agent-dashboard --skill rebuild-package-diagrams

Clone the repo

git clone --depth 1 https://github.com/BlackBeltTechnology/pi-agent-dashboard

Made for: Claude Code, Codex.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/blackbelttechnology/pi-agent-dashboard/rebuild-package-diagrams/github.svg)](https://agentmods.dev/skills/blackbelttechnology/pi-agent-dashboard/rebuild-package-diagrams)

Your own site

<a href="https://agentmods.dev/skills/blackbelttechnology/pi-agent-dashboard/rebuild-package-diagrams"><img src="https://agentmods.dev/badge/skills/blackbelttechnology/pi-agent-dashboard/rebuild-package-diagrams/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/blackbelttechnology/pi-agent-dashboard/rebuild-package-diagrams"><img src="https://agentmods.dev/badge/skills/blackbelttechnology/pi-agent-dashboard/rebuild-package-diagrams.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 94 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 5,109 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.

Model	Per session	Once invoked
Fable 5.1	$0.00094	$0.05109
Opus 5.5	$0.00038	$0.02044
Sonnet 5.5	$0.00019	$0.01022
Haiku 4.5	$0.00009	$0.00511

Measured 5d ago against content hash 27a28a6ee30d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

rebuild-package-diagrams 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.

The scan reads SKILL.md. This mod also ships 15 executable files (assets/ifml-js/ifml-navigated-viewer.production.min.js, scripts/arch.mjs, scripts/behaviour.mjs, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

packages/eng-disciplines/.pi/skills/rebuild-package-diagrams/SKILL.md · 281 lines

How it starts

The opening of the file, as written. The whole thing — 281 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Rebuild package diagrams

Turn the text of a reverse-spec-for-rebuild package into two visual views without inventing anything:

ER view — domain entities of model.md with keys and cardinality.
Process view — actor-triggered use cases of capabilities/<cap>/spec.md as BPMN 2.0.

The agent does the judgement (which entities are domain, which cardinality, which requirements form a use case). A deterministic script is the gate: it refuses any entity, field or rule id that is not in the package, any relation without evidence and any BPMN node without a resolvable ref.

Inputs

PKG = a rebuild package directory holding model.md, rules.md, quirks.md, gaps.md, capabilities/<cap>/spec.md (the reverse-spec-for-rebuild layout). Output goes to PKG/diagrams/ unless the user names another place. The source package is never edited.

D = node <this skill dir>/scripts/diagrams.mjs — subcommands extract-model, render-er, check-trace, check-use-cases, build-site (Node ≥ 20, no deps; exit 2 = bad usage/input). Parsers/gates live in scripts/lib.mjs, the catalog assembly in scripts/site.mjs, the page in templates/catalog.html, templates/catalog.css, templates/catalog.js.

Optional peers: mmdc (Mermaid CLI) for PNG/SVG; the bpmn-package-explorer skill for BPMN layout, validation and the canvas viewer. Without them the .mmd/.bpmn sources are still produced and checked.

Procedure — ER view

$D extract-model PKG/model.md > PKG/diagrams/model.json. Each entity carries capabilities, identity, persistence, persistent (heuristic: persistence line names a table/row/collection/DB), fields[] and relationships text.
Classify every entity (read identity + persistence, not only the flag) per references/er-mapping.md: domain (persisted business data or the in-memory aggregate that owns it), config, ui, test, technical. Only domain goes on the main diagram. Write the classification table to PKG/diagrams/er-scope.md (entity · class · one-line reason) so the user can overrule it.
Group domain entities into 4–8 clusters (one per subject area; capabilities are a good first cut). Clusters keep each diagram readable (≤ ~15 entities).
Author PKG/diagrams/er/<cluster>.json and one overview.json (≤ ~25 hub entities, no attributes — a 40-box overview with attributes is unreadable) in the er.json schema of references/er-mapping.md: keys (PK/FK/UK) and a few business-defining fields per entity; relations with cardinality, label, confidence, evidence. Evidence = a verbatim substring of either endpoint's Relationships: text, or the exact name of a field on either endpoint.
$D render-er PKG/diagrams/er/<x>.json PKG/diagrams/model.json > PKG/diagrams/er/<x>.mmd for each file. Exit 1 lists every violation — fix the JSON, never the check. Relations not confirmed render dashed.
Render images when mmdc exists: mmdc -i x.mmd -o x.png -b white -s 2 (see Pitfalls for the Chrome path).

Read the full file on GitHub · 281 lines

Files

What ships with it

60 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.

5d ago First seen · 281 lines · 94 tokens per session scan A 27a28a6ee30d

Subscribe to this mod's changes

rebuild-package-diagrams is a skill published in the GitHub repository BlackBeltTechnology/pi-agent-dashboard (319 stars, last pushed yesterday), licensed MIT. It adds 94 tokens to every session and 5,109 once invoked, about $0.0004 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 2026-10-11.

Design and UX Documents agent agent-framework agent-orchestration agent-skills agentic agentic-ai

goga-define-experience

Define the user experience required to achieve the established product goals and solve the identified problem.

qarium/goga · 6 tokens

akihtmlreport

Visualize a complex report that already exists in the conversation as one self-contained HTML file — nothing else, no new analysis. Distills a dense analysis/report already discussed into a single-file, ultra-wide, visually dense HTML report (REPORT.html) at the project root, for content too dense to stay legible as…

lacvietanh/akidevrule · 70 tokens

rebuild-package-diagrams