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 stark-ai-de/agent-skills --skill architecture-compassgit clone --depth 1 https://github.com/stark-ai-de/agent-skillsWrote 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/stark-ai-de/agent-skills/architecture-compass)<a href="https://agentmods.dev/skills/stark-ai-de/agent-skills/architecture-compass"><img src="https://agentmods.dev/badge/skills/stark-ai-de/agent-skills/architecture-compass/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/stark-ai-de/agent-skills/architecture-compass"><img src="https://agentmods.dev/badge/skills/stark-ai-de/agent-skills/architecture-compass.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 | $0.00094 | $0.03259 |
| Opus 5 | $0.00047 | $0.01630 |
| Sonnet 5 | $0.00019 | $0.00652 |
| Haiku 4.5 | $0.00009 | $0.00326 |
Grade A, and why
architecture-compass 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 3d 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 — 187 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Architecture Compass
Goal
Make architecture decisions explicit, binding, locally traceable, and executable. Establish repository-native governance, audit implementation, or perform an ADR-guided refactor without overwriting accepted history or broadening authority.
When to use
- Establish/reconcile ADR governance or audit architecture, decision coverage, drift, risk, and evidence.
- Plan or execute bounded ADR-governed work, including broad work that first requires durable decisions.
When not to use
- Tiny/style-only or ordinary governed edits with no architecture consequence or ADR-aware boundary check.
- Generic framework education or requests without target evidence and a governance, audit, planning, or refactoring outcome.
Activation and receipt presentation
Route activation and receipt presentation through AC-ADR-053 Short · Long · Guide. Start with Short and load Long before conditionally loading AC-INTERNAL-002 from the internal index for renderer-selection mechanics. This dispatcher does not define a presentation profile or renderer policy.
Workflow selection
Every direct invocation exposes exactly these public workflows:
setup: establish or reconcile repository-native ADR governance withrecommendedorcompletecoverage.audit: perform a strictly read-only architecture, ADR-coverage, drift, and validation assessment.refactor: execute explicit bounded work already governed by accepted local ADRs.plan-refactor: collaborate on and persist an approved bounded refactoring specification without implementing it.plan-run-refactor: plan, persist, recheck, and execute an approved broad or decision-bearing refactor.
What ships with it
60 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.
- agents/openai.yaml 891 B
- assets/adr-example.guide.md 1.5 KB
- assets/adr-example.long.md 2.3 KB
- assets/adr-example.short.md 1.1 KB
- assets/adr-index-template.md 1.3 KB
- assets/adr-template.guide.md 1.2 KB
- assets/adr-template.long.md 1.3 KB
- assets/adr-template.short.md 1.1 KB
- assets/agent-instructions-template.md 5.9 KB
- assets/new-repo-adoption-plan-template.md 6.7 KB
- assets/openai-icon.png 63 KB
- assets/refactor-report-template.md 7.0 KB
- assets/setup-report-template.md 11 KB
- references/ac-adr-001-route-architecture-compass-through-canonical-adr-triplets.guide.md 3.7 KB
- references/ac-adr-001-route-architecture-compass-through-canonical-adr-triplets.long.md 4.8 KB
- references/ac-adr-001-route-architecture-compass-through-canonical-adr-triplets.short.md 1.8 KB
- references/ac-adr-002-select-actions-resolve-authority-and-record-guardrail-adoption.guide.md 4.0 KB
- references/ac-adr-002-select-actions-resolve-authority-and-record-guardrail-adoption.long.md 6.4 KB
- references/ac-adr-002-select-actions-resolve-authority-and-record-guardrail-adoption.short.md 2.0 KB
- references/ac-adr-003-coordinate-agents-and-execute-only-approved-bounded-slices.guide.md 5.2 KB
- references/ac-adr-003-coordinate-agents-and-execute-only-approved-bounded-slices.long.md 6.4 KB
- references/ac-adr-003-coordinate-agents-and-execute-only-approved-bounded-slices.short.md 1.9 KB
- references/ac-adr-004-report-staged-evidence-and-protect-public-outputs.guide.md 4.7 KB
- references/ac-adr-004-report-staged-evidence-and-protect-public-outputs.long.md 5.9 KB
- references/ac-adr-004-report-staged-evidence-and-protect-public-outputs.short.md 1.8 KB
- references/ac-adr-005-make-repository-adrs-binding-agent-guardrails.guide.md 5.1 KB
- references/ac-adr-005-make-repository-adrs-binding-agent-guardrails.long.md 5.5 KB
- references/ac-adr-005-make-repository-adrs-binding-agent-guardrails.short.md 1.6 KB
- references/ac-adr-006-assign-workspace-ownership-and-source-roles.guide.md 4.5 KB
- references/ac-adr-006-assign-workspace-ownership-and-source-roles.long.md 5.7 KB
- references/ac-adr-006-assign-workspace-ownership-and-source-roles.short.md 1.7 KB
- references/ac-adr-007-enforce-runtime-safe-module-and-public-package-boundaries.guide.md 4.3 KB
- references/ac-adr-007-enforce-runtime-safe-module-and-public-package-boundaries.long.md 5.7 KB
- references/ac-adr-007-enforce-runtime-safe-module-and-public-package-boundaries.short.md 1.8 KB
- references/ac-adr-008-compose-nextjs-routes-rendering-and-component-responsibilities.guide.md 6.5 KB
- references/ac-adr-008-compose-nextjs-routes-rendering-and-component-responsibilities.long.md 6.6 KB
- references/ac-adr-008-compose-nextjs-routes-rendering-and-component-responsibilities.short.md 1.8 KB
- references/ac-adr-009-choose-read-query-caching-and-freshness-boundaries.guide.md 14 KB
- references/ac-adr-009-choose-read-query-caching-and-freshness-boundaries.long.md 5.3 KB
- references/ac-adr-009-choose-read-query-caching-and-freshness-boundaries.short.md 2.5 KB
- references/ac-adr-010-protect-writes-behind-validated-command-boundaries.guide.md 6.2 KB
- references/ac-adr-010-protect-writes-behind-validated-command-boundaries.long.md 4.6 KB
- references/ac-adr-010-protect-writes-behind-validated-command-boundaries.short.md 2.6 KB
- references/ac-adr-011-compose-long-running-backend-runtimes-and-lifecycles-explicitly.guide.md 27 KB
- references/ac-adr-011-compose-long-running-backend-runtimes-and-lifecycles-explicitly.long.md 5.0 KB
- references/ac-adr-011-compose-long-running-backend-runtimes-and-lifecycles-explicitly.short.md 2.7 KB
- references/ac-adr-012-resolve-environment-and-configuration-at-deployable-boundaries.guide.md 4.6 KB
- references/ac-adr-012-resolve-environment-and-configuration-at-deployable-boundaries.long.md 4.8 KB
- references/ac-adr-012-resolve-environment-and-configuration-at-deployable-boundaries.short.md 2.2 KB
- references/ac-adr-013-own-language-package-build-lint-and-supply-chain-tooling-explicitly.guide.md 6.7 KB
- references/ac-adr-013-own-language-package-build-lint-and-supply-chain-tooling-explicitly.long.md 5.9 KB
- references/ac-adr-013-own-language-package-build-lint-and-supply-chain-tooling-explicitly.short.md 2.3 KB
- references/ac-adr-014-select-application-runtimes-deployment-hosts-and-additional-targets-by-evidence.guide.md 6.3 KB
- references/ac-adr-014-select-application-runtimes-deployment-hosts-and-additional-targets-by-evidence.long.md 5.4 KB
- references/ac-adr-014-select-application-runtimes-deployment-hosts-and-additional-targets-by-evidence.short.md 2.1 KB
- references/ac-adr-015-select-frontend-capability-libraries-by-product-need.guide.md 4.6 KB
- references/ac-adr-015-select-frontend-capability-libraries-by-product-need.long.md 5.5 KB
- references/ac-adr-015-select-frontend-capability-libraries-by-product-need.short.md 2.7 KB
- references/ac-adr-016-select-ai-model-streaming-ui-and-agent-capabilities-deliberately.guide.md 4.9 KB
- references/ac-adr-016-select-ai-model-streaming-ui-and-agent-capabilities-deliberately.long.md 6.0 KB
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.
- 3d ago Changed 6971ae62e55e
- 12d ago First seen · 187 lines · 94 tokens per session scan A 49f9a99c0cd8
architecture-compass is a skill published in the GitHub repository stark-ai-de/agent-skills (5 stars, last pushed 2d ago), licensed Apache-2.0. It adds 94 tokens to every session and 3,259 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
openlore-brainstorm
Transform a feature idea into an annotated story using a Domain Sketch or Constrained Option Tree. Use when asked to brainstorm, explore, or shape a feature before implementation.
openlore-execute-refactor
Apply a confirmed .openlore/refactor-plan.md with a test gate after each change. Use when asked to execute or continue an OpenLore refactoring plan.
openlore-plan-refactor
Identify a high-priority refactoring target, assess its blast radius, and write .openlore/refactor-plan.md without changing code. Use when asked to plan or prioritize a refactor.
openlore-debug
Debug with OpenLore structural context, an explicit root-cause hypothesis, and RED/GREEN verification. Use when a bug, failure, or regression needs diagnosis and repair.
openlore-implement-story
Implement a brownfield story with OpenLore orientation, risk checks, spec validation, tests, and drift detection. Use when asked to implement or continue a story in an existing codebase.
openlore-write-tests
Write and run real tests for a function or spec scenario after reading implementation and contract evidence. Use when asked to add, improve, or repair tests without stubs or placeholders.