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 agentmods add rules/pallerana/agentic-loop-engineering-kit/service-quality-drillgit clone --depth 1 https://github.com/pallerana/agentic-loop-engineering-kitWrote 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/pallerana/agentic-loop-engineering-kit/service-quality-drill)<a href="https://agentmods.dev/rules/pallerana/agentic-loop-engineering-kit/service-quality-drill"><img src="https://agentmods.dev/badge/rules/pallerana/agentic-loop-engineering-kit/service-quality-drill.svg" alt="Measured on agentmods" 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 | $0.00689 | $0.00689 |
| Opus 5 | $0.00345 | $0.00345 |
| Sonnet 5 | $0.00138 | $0.00138 |
| Haiku 4.5 | $0.00069 | $0.00069 |
Grade A, and why
service-quality-drill 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 — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Service Quality Drill
Applies to Java/Gradle services in consumer monorepos using the Agentic Loop Engineering Kit.
Also follow java-springboot-standards.mdc for coding patterns, layering, and ArchUnit rules.
Quality drill — every change
- Implement — smallest correct fix; match repo conventions; no speculative refactors.
- Regression test — unit for branches; integration/WebMvcTest/WireMock for wiring and HTTP contracts. Every Copilot/CodeQL thread must cite a named test.
- Local build:
./gradlew clean buildfrom the repo root (full suite — not-x test). - JaCoCo gate — read
build.gradle.ktsin the repo you are changing:- Default line ratio ≥ 0.80 unless
build.gradle.ktsstates otherwise — never assume; do not inflate exclusions to pass the gate. - High-coverage services (e.g. MVP repos): ≥ 1.00 on measured packages when profile
jacoco_line_ratiorequires it. - On failure: inspect
build/reports/jacoco/jacocoTestReport.htmland add tests for uncovered measured lines.
- Default line ratio ≥ 0.80 unless
- ce-code-review vs
main— fix all P0/P1 before commit. For PR reviews, follow pr-code-review.mdc. - Commit only when the user asks; batch logically.
- Push once per batch (minimize CI workflow runs).
- CI green:
gh pr checks <n> --repo <org>/<repo-name>— wait for:lint,build-and-test,Trivy,dependency-review,gitleaks,CodeQL
- Review threads: fix in code + test → reply → resolve. No “follow-up only” replies without implementation.
- Wiki writeback (when LLM-wiki is installed): append
docs/wiki/log.md, updatedocs/wiki/current-status.mdfor durable outcomes.
Required merge checks (common across repos)
Branch protection on main expects the CI checks above plus code-owner reviews, conversation resolution, and linear history. CodeQL uses GitHub default setup — do not add a duplicate CodeQL workflow file.
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 First seen · 47 lines · 689 tokens per session scan A faa7940c6983
service-quality-drill is a cursor rule published in the GitHub repository pallerana/agentic-loop-engineering-kit (4 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 689 tokens to every session, about $0.0034 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 cursor rules, from other repositories
workflow
BDD-style workflow, UI screenshots in the PR, HTTP OpenAPI and config schema sync before lint, final checks.
stackhawk-hawkscan-ci-failure
HawkScan CI failure semantics reference: exit codes 0/1/42, failureThreshold tuning, block-on-42 vs warn-only vs scheduled-baseline modes, retry strategy (don't retry 42), caching strategy (cache CLI/image, never findings), scheduled-vs-PR-trigger tradeoffs.
github-actions
GitHub Actions workflow guidelines.
adr-004
Cursor rule "adr-004" from actual-software/actual-cli, covering adopt secure secrets management in ci/cd pipeline and policies.
workflow-ci
Testing and verification workflow expectations.
linting-and-formatting
Linting, formatting, pre-commit, and CI enforcement.