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-dependencies)<a href="https://agentmods.dev/skills/melodic-software/claude-code-plugins/map-dependencies"><img src="https://agentmods.dev/badge/skills/melodic-software/claude-code-plugins/map-dependencies/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-dependencies"><img src="https://agentmods.dev/badge/skills/melodic-software/claude-code-plugins/map-dependencies.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 | $0.00081 | $0.03756 |
| Opus 5.5 | $0.00032 | $0.01502 |
| Sonnet 5.5 | $0.00016 | $0.00751 |
| Haiku 4.5 | $0.00008 | $0.00376 |
Grade A, and why
map-dependencies 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 — 269 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository context
The current repository is the default subject. Collect its root with one Bash call,
git rev-parse --show-toplevel. Treat a failure as an unknown root and ask for a path.
Do not walk the working directory for nested repositories.
Purpose
Answer "which project depends on which, and in which direction" from build declarations
a script read. Every edge names the file and the declaration it came from. The canonical
artifact is dependency-graph.json. The human render is a mermaid flowchart of the
internal edges. This is the model, not a C4 diagram.
The dialect decision lives in ${CLAUDE_PLUGIN_ROOT}/reference/config.md. Read it.
Do not restate it, and do not emit a C4 view from this skill. This flowchart does
not follow landscape_dialect. diagram_dialect.system stays the planning opt-in.
Resolve home
Read ${CLAUDE_PLUGIN_ROOT}/reference/config.md for architecture_dir. Run
bash "${CLAUDE_PLUGIN_ROOT}/lib/resolve-convention-home.sh" --root "${CLAUDE_PROJECT_DIR}"
and follow the exit code. Never parse the root instruction file yourself.
--out <dir> wins for this run alone. Then a declared architecture_dir. With neither,
including every non-interactive run, stop and point at /architecture:setup. This skill
never writes the topic doc.
Build the graph
"${CLAUDE_SKILL_DIR}/scripts/dependency-graph.sh" \
--out "<architecture_dir>/dependency-graph.json" "<repo-path>"
The script writes the record itself and exits 1 when it cannot. generated_on is the
HEAD commit date (unknown with no commit), so a second run on the same commit is
byte-identical; --generated-on <date> overrides it. The document is one object per
line. Do not pretty-print it. A reader given another layout exits 1.
result is ok or unknown. unknown means no shipped adapter could read the tree.
The message says which manifests were found. That is the answer. Do not draw a diagram,
and do not fill the arrays by hand. An empty graph is result ok with project nodes
and no edges. Read it as a repository that declares no references only when no
unread-reference-tags or unread-manifest finding exists. The first means the collector
skipped reference tags in a file, and the edge list is short by that count. The second
means a manifest holds a declaration whose shape no reader handles; its evidence is the
file, a colon, and the declaration skipped, one finding per declaration.
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 · -12 tokens per session a3e206d6d8b3
- 12d ago Changed · +7 lines 226e426984a2
- 15d ago Changed · +96 lines 91811748cd87
- 16d ago Changed · +28 lines 992544393d9f
- 17d ago First seen · 138 lines · 93 tokens per session scan A 26d56aea00ce
map-dependencies is a skill published in the GitHub repository melodic-software/claude-code-plugins (25 stars, last pushed today), licensed MIT. It adds 81 tokens to every session and 3,756 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
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.
optimize-local-search
For NP-hard optimization: TSP, scheduling, assignment problems. Uses greedy construction + local improvement (2-opt, hill climbing).
pass-function-as-arg
For generic algorithms: strategy pattern, callbacks, configurable behavior. Pass functions as parameters to customize algorithm behavior.
solve-constraint-puzzle
For constraint satisfaction: Sudoku, scheduling, N-queens, logic puzzles, SAT-like problems, assignment problems. Uses propagate-then-search pattern.
test-with-examples
For example-driven development: test cases as specifications, input/output pairs, documentation through examples.