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 atretyak1985/swarmery/plugin install architecture-packWrote 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/atretyak1985/swarmery/architecture-map)<a href="https://agentmods.dev/skills/atretyak1985/swarmery/architecture-map"><img src="https://agentmods.dev/badge/skills/atretyak1985/swarmery/architecture-map/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/atretyak1985/swarmery/architecture-map"><img src="https://agentmods.dev/badge/skills/atretyak1985/swarmery/architecture-map.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 | $0.00097 | $0.02518 |
| Opus 5 | $0.00048 | $0.01259 |
| Sonnet 5 | $0.00019 | $0.00504 |
| Haiku 4.5 | $0.00010 | $0.00252 |
Grade A, and why
architecture-map scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 199 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Architecture Map
Produce <repo>/architecture-out/architecture-map.json + .html. The JSON is the
source of truth; the HTML is rendered from it by scripts/build.sh — never write
HTML by hand.
0. Freshness gate (always first)
Which of the two shapes you are in decides everything below: a single repo
(the working directory is itself a checkout — .git exists) or a multi-repo
workspace (no .git at the root; the member checkouts are listed in
.claude/project.json → repos[], and module paths are workspace-relative,
<repo>/<path-inside-it>).
Single repo
HEAD=$(git rev-parse HEAD)
LAST=$(node -e "try{const v=JSON.parse(require('fs').readFileSync('architecture-out/architecture-map.json')).analyzedAtCommit;console.log(typeof v==='string'&&v.length>=7?v:'')}catch{console.log('')}")
LAST == HEAD→ report "architecture map is up to date (commit )" and STOP.LASTnon-empty → incremental mode:git diff --name-only $LAST..HEAD→ map changed paths onto existingmodules[].pathprefixes; re-describe ONLY touched modules, re-check only flows whose steps reference them; keep the rest.LASTempty → full analysis.
Multi-repo workspace
There is no single HEAD to compare against, so compare PER MEMBER against the
map's optional analyzedAtCommits object ({"<repo>": "<sha>"}):
# One member per LINE — a member directory may contain spaces.
node -e "try{const r=JSON.parse(require('fs').readFileSync('.claude/project.json')).repos;if(Array.isArray(r))console.log(r.join('\n'))}catch{}" |
while IFS= read -r repo; do
[ -n "$repo" ] || continue
[ -e "$repo/.git" ] || { echo "$repo: not a checkout — skipping"; continue; }
head=$(cd "$repo" && git rev-parse HEAD)
last=$(node -e "try{const m=JSON.parse(require('fs').readFileSync('architecture-out/architecture-map.json')).analyzedAtCommits||{};const v=m[process.argv[1]];console.log(typeof v==='string'&&v.length>=7?v:'')}catch{console.log('')}" "$repo")
echo "$repo $last $head"
done
What ships with it
6 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 · +63 lines 3f23181f0354
- 10d ago First seen · 136 lines · 97 tokens per session scan A 50a67e47d8d8
architecture-map is a skill published in the GitHub repository atretyak1985/swarmery (5 stars, last pushed today), licensed Apache-2.0. It adds 97 tokens to every session and 2,518 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
notebooklm
Programmatic access to Google NotebookLM for creating notebooks, adding sources (URLs, YouTube, PDFs, audio, video, images), chatting with content, generating artifacts (podcasts, videos, reports, quizzes, mind maps, flashcards, infographics), and downloading results. Includes capabilities beyond the web UI.
gh-address-comments
This skill should be used when addressing GitHub pull request review comments systematically with mandatory resolution tracking. Use when user says "address PR comments", "fix review feedback", "handle PR review", "resolve PR threads", or needs to ensure all review comments are addressed before merging. Fetches…
prowlarr
Search indexers and manage Prowlarr. Use when the user asks to "search for a torrent", "search indexers", "find a release", "check indexer status", "list indexers", "prowlarr search", "sync indexers", or mentions Prowlarr/indexer management.
sonarr
This skill should be used when managing TV shows in Sonarr. Use when the user asks to "add a TV show", "search Sonarr", "find a series", "add to Sonarr", "remove a show", "check if show exists", "Sonarr library", "TVDB lookup", or mentions TV show management or Sonarr operations.
commit-message
Use ANY time the user signals they want to commit staged changes — including bare "commit", "/commit", "commit this", "commit these changes", "let's commit", "make a commit", "git commit", "write a commit message", "make a conventional commit", "use conventional commits", or any equivalent phrasing in context (e.g.…
dependency-versions
MUST consult this skill before answering whenever the user's task involves external versioned dependencies — even if you think you can handle it directly. This applies to: checking if packages/tools are up to date, upgrading npm/pip/cargo/go dependencies, planning or writing CI/CD workflows (GitHub Actions, CircleCI…