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-events)<a href="https://agentmods.dev/skills/melodic-software/claude-code-plugins/map-events"><img src="https://agentmods.dev/badge/skills/melodic-software/claude-code-plugins/map-events/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-events"><img src="https://agentmods.dev/badge/skills/melodic-software/claude-code-plugins/map-events.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 | $0.00082 | $0.02202 |
| Opus 5.5 | $0.00033 | $0.00881 |
| Sonnet 5.5 | $0.00016 | $0.00440 |
| Haiku 4.5 | $0.00008 | $0.00220 |
Grade A, and why
map-events 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 — 153 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 and the DEFAULT SUBJECT. Collect the project root with
one Bash call, git rev-parse --show-toplevel. A failure is an unknown value; ${CLAUDE_PROJECT_DIR}
is the root either way.
Purpose
Answer "who publishes which message, and who consumes it" from committed C# call sites and handler registrations. Every edge cites a file and a line. The scripts collect and render. Do not add an edge the script did not emit, and do not drop a publish whose contract type did not resolve.
The shipped adapter is the MassTransit shape: Publish<T> or Publish(new T(..)) is broadcast,
Send<T> or Send(new T(..)) is point-to-point, IConsumer<T> consumes T. AddConsumer<C> and
ConfigureConsumer<C> register the consumer class C; they are not messages. Inside a
ReceiveEndpoint("q", ..) call, on its own line or in its block, they put C's consume edges on
queue q; a registration outside it and every publish or send edge has no queue. A message is a type some
publish, send, or consume names; a service or consumer class is not one. Identity is the
namespace-qualified type. In-process calls are /architecture:map-flow. A cross-process hop in
that trace is a hand-off to this skill.
Read: C# (MassTransit shape). Declined: Node, Go, Python, Rust, JVM, Ruby, and PHP. Their files are never read, so a message only they publish or consume is absent from the chart, not a finding.
Resolve home
Read ${CLAUDE_PLUGIN_ROOT}/reference/config.md first. This skill writes into architecture_dir.
It reads no dialect key and adds none: it always writes events.md, a mermaid flowchart (dotted
broadcast, solid point-to-point). The authoring-formats convention keys a dialect only for data
diagrams and C4 system views. A message-topology flowchart is neither, so it follows the unkeyed
mermaid rule, as /planning:design's sequence flows do.
Run bash "${CLAUDE_PLUGIN_ROOT}/lib/resolve-convention-home.sh" --root "${CLAUDE_PROJECT_DIR}".
Exit 0 means read <home>/architecture/README.md for architecture_dir. Exit 1, 2, and 3 mean
there is no declared home.
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 · -3 tokens per session 5117f40a028f
- 11d ago Changed · +1 lines 1bb3761919b4
- 12d ago Changed · +7 lines 5210c37d1978
- 14d ago Changed · +3 lines 7d4285c6edcc
- 16d ago Changed · +8 lines 49d49f02e5d4
- 17d ago First seen · 134 lines · 85 tokens per session scan A 60bc71b761e0
map-events is a skill published in the GitHub repository melodic-software/claude-code-plugins (25 stars, last pushed today), licensed MIT. It adds 82 tokens to every session and 2,202 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 2026-09-29.
Other skills, from other repositories
cascade-type-conversion
For flexible parsing: try multiple type conversions in order, graceful fallback from specific to general types.
find-shortest-path
For pathfinding and search: shortest path, maze solving, game AI, route planning, graph traversal, BFS/DFS, Dijkstra, A problems.
pass-function-as-arg
For generic algorithms: strategy pattern, callbacks, configurable behavior. Pass functions as parameters to customize algorithm behavior.
catch-expected-errors
For iteration with errors: catch exceptions during exploration, skip invalid cases, continue to next attempt.
rust-coding-standards
Rust coding standards, documentation authoring, content workflows, and quality patterns for systemprompt.io development.
visual-design-system
World-class visual design system standards — OKLCH color science, fluid typography, elevation hierarchy, branded asymmetric corners, and dark mode implementation.