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.
npx skills add adam-s-k-i/super-backlog --skill architecture-summarygit clone --depth 1 https://github.com/adam-s-k-i/super-backlogWrote 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/adam-s-k-i/super-backlog/architecture-summary)<a href="https://agentmods.dev/skills/adam-s-k-i/super-backlog/architecture-summary"><img src="https://agentmods.dev/badge/skills/adam-s-k-i/super-backlog/architecture-summary/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/adam-s-k-i/super-backlog/architecture-summary"><img src="https://agentmods.dev/badge/skills/adam-s-k-i/super-backlog/architecture-summary.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 | $0.00058 | $0.01075 |
| Opus 5.5 | $0.00023 | $0.00430 |
| Sonnet 5.5 | $0.00012 | $0.00215 |
| Haiku 4.5 | $0.00006 | $0.00108 |
Grade A, and why
architecture-summary 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.
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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Architecture Summary: curate the project summary page
Writes backlog/docs/architecture.yml. The dashboard hub renders it at
/p/<slug>/summary/ next to facts it computes itself (versions, LOC, tests,
releases, CI, open work). Schema and YAML subset:
https://adam-s-k-i.github.io/super-backlog/guide/project-summary.
When this skill runs
- The user asks for a project summary, an architecture overview or a diagram.
- The summary page shows "No architecture file yet".
- After structural changes: new modules, removed components, renamed commands.
sbl summaryreports drift.
Procedure
- Read the facts first: manifests (
package.json,composer.json, WordPress headers instyle.cssor the main plugin file), the top-level directory layout, the entry points, and the test layout. - If
backlog/docs/architecture.ymlexists, runsbl summaryfirst and read the file. Fix every finding it lists: remove or correct paths that no longer exist (missing-path), prunetasksentries for Done or unknown tasks (done-task,unknown-task), and refresh the nodes whose code changed (stale-file). Keep curated prose (pitch,purpose,why, highlight texts) unless the code contradicts it; change only what is outdated or missing. - Propose the content:
pitch: one or two sentences,**bold**is the only markup.- 6 to 14
nodeswithkind, a shortlabel, an optionalsub,purpose,why, realfilesand realcommands. Keeplabelat 18 characters or fewer andsubat 20 or fewer so they fit the node box; 28 and 32 are only the hard schema limits, and longer text is clipped with an ellipsis. zonesthat group nodes by layer; zones may not overlap.edgesthat read "from → label → to" (the source uses, calls or writes the target).- 3 to 5
flowsthat walk existing edges, each step written asfrom>to. - 4 to 6
highlights, at most one per node. stack,commandsandtasks(open task id → node id) where they help.
- Place nodes on the
gridso that every edge is a straight line or has a single corner: connected nodes share a row or a column, or the corner cell between them stays free. - Write the file with two-space indentation, no tabs, and quote every plain
value that contains a comma inside
{ }or[ ], a colon followed by a space, or a#after a space, that ends with a colon, or that starts with a dash and a space (or is a bare dash). A#starts a comment only after a space, also after a quoted value or a flow collection. - Run
sbl doctor. Check 5 validates the file and prints every problem with its path, plus the layout warnings (route-fallback,label-collision,crossing,port-overflowfor too many connections on one side of a box). Fix the file and runsbl doctoragain until check 5 reports[ok], or only its drift line remains. - Run
sbl summary, fix every drift finding it lists and run it again. Finish when it exits 0, or 4 only for warnings the user accepts. Astale-filefinding clears only once the refreshed file is committed, so after a refresh it is the one finding that may remain. - Present the diff of
backlog/docs/architecture.ymlfor review and STOP until the user approves the prose. Point to the live page:sbl dashboard, then the Summary tab.
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 Changed · +4 lines e652021e63c7
- 6d ago First seen · 73 lines · 58 tokens per session scan A ee764106a6bf
architecture-summary is a skill published in the GitHub repository adam-s-k-i/super-backlog (2 stars, last pushed 2d ago), licensed MIT. It adds 58 tokens to every session and 1,075 once invoked, about $0.0002 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.
Other skills, from other repositories
link-ticket-to-session
Link the current Claude Code session to a ticket (Linear, Jira, GitHub Issues, or GitHub Pull Requests) and cache its title/status in karma. Use when the user explicitly asks to link, attach, associate, or connect this session to a ticket, issue, or PR — e.g. "/link-ticket-to-session ABC-123", "link this session to…
lens-dashboard
Design and spec an analytical dashboard — define the question each chart answers, write the SQL queries, spec the layout and refresh cadence. Produces a complete dashboard spec ready to implement. Use when asked to "build a dashboard", "analytics dashboard", "BI dashboard", "weekly product health", or "visualize this…
prism-dashboard
Build an internal dashboard with data tables, filters, detail views, and CRUD. Use when asked to build an "admin panel", "internal dashboard", "back office", or "data dashboard UI".
delegate
Let Claude Architect route a versioned implementation spec through the trusted MCP runtime, independently review the Candidate Artifact, record a decision, and integrate only accepted bytes. Use for implementation delegation, Producer selection, or commitment-boundary review.
subagent-driven-delegation
Execute an implementation plan with the Superpowers subagent-driven-development loop while every task is implemented by a verified Claude Architect Producer — isolated worktree, frozen Candidate Artifact, independent verification, fresh-context review, runtime-gated acceptance. Use when executing a multi-task plan…
fleet-doctrine
Fleet Deck doctrine — how to behave as one Claude Code session among many on this machine. Use when you see [FLEETDECK] messages in context, when told to coordinate with / message / answer another session, when asked about the fleet board, or when deputized to decide something for another session.