Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add melodic-software/claude-code-plugins/plugin install architectureWrote 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/melodic-software/claude-code-plugins/map-data)<a href="https://agentmods.dev/skills/melodic-software/claude-code-plugins/map-data"><img src="https://agentmods.dev/badge/skills/melodic-software/claude-code-plugins/map-data/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/melodic-software/claude-code-plugins/map-data"><img src="https://agentmods.dev/badge/skills/melodic-software/claude-code-plugins/map-data.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 | $0.00091 | $0.04251 |
| Opus 5.5 | $0.00036 | $0.01700 |
| Sonnet 5.5 | $0.00018 | $0.00850 |
| Haiku 4.5 | $0.00009 | $0.00425 |
Grade A, and why
map-data 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 yesterday.
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 — 257 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository context
The current repository is both the CONSUMER, whose convention home declares where artifacts land, and the DEFAULT SUBJECT, whose tracked files declare the schema.
Collect with an individual Bash call, one command per call: the project root,
git rev-parse --show-toplevel. Treat a failure (not a repository, git unavailable) as an unknown
value and carry on; ${CLAUDE_PROJECT_DIR} is the resolver's --root either way.
Purpose
Answer "what are the entities and how do they relate" from declarations in the tree. Every entity and every cardinality traces to a named file. The scripts collect and render. Do not draw a box the script did not emit, and do not invent a cardinality the script did not record.
This is not a C4 diagram. The C4 set is system context, containers, components, and code, plus system landscape, dynamic, and deployment. An entity-relationship diagram is none of those.
Resolve home and dialect
Read ${CLAUDE_PLUGIN_ROOT}/reference/config.md first. This skill writes into architecture_dir.
It does not read landscape_dialect and adds no dialect key: the diagram dialect is
diagram_dialect.data from the authoring-formats topic doc.
Run bash "${CLAUDE_PLUGIN_ROOT}/lib/resolve-convention-home.sh" --root "${CLAUDE_PROJECT_DIR}" and
follow the exit code; never parse the root instruction file yourself. Exit 0: read
<home>/architecture/README.md for architecture_dir. Exit 1, 2, or 3: no declared home.
Per key, in order: --out <dir> wins for this run alone, then a declared architecture_dir, then
one question. architecture_dir has NO default. An undeclared and unconfirmed home, including
every non-interactive run, STOPS and points at /architecture:setup. Do not invent a directory.
Resolve diagram_dialect.data by restating this ladder, then running the resolver rather than
parsing the topic doc yourself. The ladder is a resolution order, not a task list:
1. Anchor at the repository root: `${CLAUDE_PROJECT_DIR}` when set, otherwise
`git rev-parse --show-toplevel`. Never a CWD-relative read.
2. Resolve the convention home `<home>` with the bundled resolver above. Never hand-parse the root
file.
3. The printed home is repo-relative: join it to the root, then pass
`<root>/<home>/authoring-formats/README.md` to the resolver.
4. Layer order is one layer deep: an explicit `--dialect` argument, then the team convention doc,
then the documented default `mermaid`. There is no personal overlay.
5. Default: `diagram_dialect.data` is `mermaid`. Allowed values are `mermaid` and `dbml`.
6. Degrade soft, and say so. No pointer, no doc, no key, or an unrecognized value each resolve to
`mermaid`. The resolver names the cause on stderr. Do not hard-fail and do not ask the operator
to create the surface mid-task.
7. Report provenance: the key, the value, and the layer (`argument`, `team convention doc <path>`,
or `default`).
What ships with it
4 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.
- yesterday Changed · -2 lines · -3 tokens per session d8890e0b17e4
- 11d ago Changed · +1 lines 60b3f020c0f5
- 12d ago Changed · +7 lines ec9132cdea51
- 15d ago Changed · +20 lines 60fc55832f70
- 16d ago Changed · +44 lines · +11 tokens per session e494fdd4dc60
- 17d ago First seen · 187 lines · 83 tokens per session scan A aee079c59f1c
map-data is a skill published in the GitHub repository melodic-software/claude-code-plugins (25 stars, last pushed today), licensed MIT. It adds 91 tokens to every session and 4,251 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 2026-09-29.
Other skills, from other repositories
db-schema-migrations
Add or change DB columns in the marketplace extension: update the base schema SQL, write an idempotent migration, register it in schemas.rs, regenerate the sqlx offline cache, and verify local + prod DB match.
db-sync-prod-to-local
Sync a systemprompt.io project's production Postgres data into the local dev DB. Covers two failure modes: TLS ALPN rejection (libpq 17+) and cloud-profile path mismatch (/app does not exist locally).
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…
parallel-worker
Execute focused implementation tasks in a parallel workflow. Use when: working on assigned files in a worktree, making checkpoint commits, signaling dependencies or blockers, completing orchestrator-assigned tasks. Triggers: worker, checkpoint, worktree, assigned scope, commit prefix, parallel task.
find-shortest-path
For pathfinding and search: shortest path, maze solving, game AI, route planning, graph traversal, BFS/DFS, Dijkstra, A problems.
optimize-local-search
For NP-hard optimization: TSP, scheduling, assignment problems. Uses greedy construction + local improvement (2-opt, hill climbing).