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.
git clone --depth 1 https://github.com/loiane/specs-driven-development-spring-angularWrote 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/rules/loiane/specs-driven-development-spring-angular/always-on)<a href="https://agentmods.dev/rules/loiane/specs-driven-development-spring-angular/always-on"><img src="https://agentmods.dev/badge/rules/loiane/specs-driven-development-spring-angular/always-on/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/rules/loiane/specs-driven-development-spring-angular/always-on"><img src="https://agentmods.dev/badge/rules/loiane/specs-driven-development-spring-angular/always-on.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 | $0.00024 | $0.00978 |
| Opus 5.5 | $0.00010 | $0.00391 |
| Sonnet 5.5 | $0.00005 | $0.00196 |
| Haiku 4.5 | $0.00002 | $0.00098 |
Grade A, and why
always-on 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 4d 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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Always-on rules
You are working in a workspace governed by docs/methodology.md (seven-phase spec-driven workflow) and docs/harness-principles.md (the agent validates its own work).
Read-first
At the start of every session, read:
docs/methodology.mddocs/harness-principles.mddocs/artifact-contract.mddocs/spec-format.md- The active feature's
.specs/<feature-id>/files, in numerical order.
Hard rules — phases 1–3 (no invention)
- Never invent a default. When you would otherwise pick one (DB engine, auth, error envelope, pagination, units, currency, retention, etc.), append a
Q-NNNto the active artifact's## Open Questionsand halt for the user. - Quote source tickets verbatim.
- Stable IDs —
AC-NNN,T-NNN,Q-NNNare never renumbered. - For Epic-sized work, produce
03-epic-design.mdand03a-epic-roadmap.mdbefore detailed slice-level03-design.mdand04-tasks.md.
Hard rules — phase 4 (TDD)
- Before any edit to
src/main/**, read.specs/<active-feature>/.tdd-state.json. Refuse the edit unless the active task'sphase == "red"andred_failure_excerptis non-empty AND the file is infiles_in_scope. - If you discover the precondition is not met, run the matching workflow first (e.g. invoke
spring-test-engineerto write the failing test). - Never use
-DskipTests,-Dpit.skip,-Dcheckstyle.skip,-Dspotbugs.skip,--no-verify. - Never delete a test or remove an assertion.
- Never add
@Disabledwithout a# DisabledReason: <link>on the line above. - Never lower a coverage threshold.
Hard rules — phases 6 and 7
spring-validatorandspring-code-reviewernever edit production code or tests; they only write the validation/review artifact.- A skipped test without
# DisabledReason= error. - A missing report for a configured layer = error.
- Every waiver references an ADR.
Spring Boot 4 conventions
Apply .windsurf/skills/spring-boot-4-conventions/SKILL.md, archunit-rules/SKILL.md, spring-security-baseline/SKILL.md.
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.
- 4d ago First seen · 67 lines · 24 tokens per session scan A e2bfe4665261
always-on is a cursor rule published in the GitHub repository loiane/specs-driven-development-spring-angular (62 stars, last pushed 3d ago), licensed MIT. It adds 24 tokens to every session and 978 once invoked, about $0.0001 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 2026-10-12.
Other cursor rules, from other repositories
e2e_tests
Java SDK End to End Tests.
tdd-guide
Cursor rule "tdd-guide" from ulises-jeremias/agent-toolkit, covering agent vs skill rule — why agent (cite clause), when to use vs holistic, caller / skills / handoff, the tdd cycle and when invoked.
development-process
Mandatory agentic development process — feature analysis, architecture design, task break, approval, TDD.
test-driven-development
Cursor IDE Config for Test Driven Development (TDD) and generating Specifications before each new feature.
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.
angular-20
This rule provides comprehensive best practices and coding standards for Angular development, focusing on modern TypeScript, standalone components, signals, and performance optimizations.