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 alexei-led/architect --skill architecture-scorecardgit clone --depth 1 https://github.com/alexei-led/architectWrote 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/alexei-led/architect/architecture-scorecard)<a href="https://agentmods.dev/skills/alexei-led/architect/architecture-scorecard"><img src="https://agentmods.dev/badge/skills/alexei-led/architect/architecture-scorecard/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/alexei-led/architect/architecture-scorecard"><img src="https://agentmods.dev/badge/skills/alexei-led/architect/architecture-scorecard.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 | $0.00071 | $0.01306 |
| Opus 5 | $0.00036 | $0.00653 |
| Sonnet 5 | $0.00014 | $0.00261 |
| Haiku 4.5 | $0.00007 | $0.00131 |
Grade A, and why
architecture-scorecard 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 9d 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 — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Architecture scorecard
How to score, honestly and reproducibly. The rubric itself lives in
../../resources/templates/scorecard.yaml — read it; do not restate or invent values here.
When to use
Use whenever you are about to assign or revise a score on any architecture dimension. The architecture-review skill calls this before writing scores into a report.
Skill navigation
- Missing evidence or system map: return to
architecture-review; scores are not a substitute for evidence. - Current skill: use
architecture-scorecardonly to assign defensible values, bands, confidence, and score rationales. - Next skill: write the
architecture-reviewreport, then recommend one primary next step:architecture-designwhen findings need target-state decisions,architecture-planonly when an approved design already exists and sequencing is requested, or no next skill for pure audit/scoring.
Procedure
-
Read the rubric.
../../resources/templates/scorecard.yamlis the source of truth for dimension names, 0..100 bands and their anchors, confidence levels, and the enforced rules. If you find yourself typing a dimension name or band edge from memory, stop and read the file — drift from the scorecard is a bug. -
Per dimension, gather the evidence first. A score with no evidence ref is invalid for every non-meta dimension. If you have no evidence, do not score — record a coverage gap and let
analysis_confidenceabsorb it. Absence of findings counts as positive evidence only when a current tool actually covered that finding class. -
Pick the band, then the value. Choose the band whose anchor best fits the evidence first. Then choose a 0..100 value within that band; default to the band midpoint unless the evidence clearly supports an edge. The band must be the one whose range contains the value. Band and value disagreeing is a hard error.
-
Set confidence independently of quality. Confidence reflects how trustworthy the assessment is — coverage, recency, directness of evidence — not how good the architecture is. Missing or failed tools lower it.
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.
- 9d ago First seen · 122 lines · 71 tokens per session scan A 5f983b3766b3
architecture-scorecard is a skill published in the GitHub repository alexei-led/architect (2 stars, last pushed 1mo ago), licensed MIT. It adds 71 tokens to every session and 1,306 once invoked, about $0.0004 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
code-review-excellence
This skill should be used when the user asks to review a diff or pull request, write review comments, audit code quality, establish review standards, or improve how a team performs code review.
new-skill
Scaffold a new brooks-lint analysis skill so it passes npm run validate and npm run evals on the first try — generates skills/{name}/SKILL.md (with the mandatory "Do NOT trigger for:" clause and a Process section citing guide step ranges) plus skills/{name}/{name}-guide.md (sequentially numbered steps), then appends…
release
Cut a brooks-lint release: set the version in package.json, propagate it across all four plugin manifests and every version-bearing text file (README badges, docs site metadata), write the CHANGELOG entry, validate, then commit, push, tag, and publish the GitHub release. Triggers when the maintainer asks to "release"…
brooks-sweep
Full-sweep mode: runs a unified analysis across all quality dimensions — code decay, architecture, tech debt, and test quality — then applies fixes directly to the codebase. Safe changes are auto-applied; risky changes are confirmed before execution. Drawing on twelve classic engineering books. Triggers when: user…
brooks-test
Test quality review drawing on twelve classic engineering books — with primary focus on xUnit Test Patterns, The Art of Unit Testing, How Google Tests Software, and Working Effectively with Legacy Code — that diagnoses structural problems in an existing test suite: brittleness, mock abuse, coverage illusions, slow…
software-design-review
Critically review a software design specification and suggest concrete improvements. Use when the user wants to review, critique, audit, evaluate, or strengthen a design spec, technical specification, feature design, architecture proposal, or implementation plan. Focus on clarity, completeness, correctness…