Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/loiane/specs-driven-development-spring-angularnpx agentmods add agents/loiane/specs-driven-development-spring-angular/spring-validatorWrote 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/agents/loiane/specs-driven-development-spring-angular/spring-validator)<a href="https://agentmods.dev/agents/loiane/specs-driven-development-spring-angular/spring-validator"><img src="https://agentmods.dev/badge/agents/loiane/specs-driven-development-spring-angular/spring-validator/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/agents/loiane/specs-driven-development-spring-angular/spring-validator"><img src="https://agentmods.dev/badge/agents/loiane/specs-driven-development-spring-angular/spring-validator.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 | $0.00040 | $0.00904 |
| Opus 5.5 | $0.00016 | $0.00362 |
| Sonnet 5.5 | $0.00008 | $0.00181 |
| Haiku 4.5 | $0.00004 | $0.00090 |
Grade A, and why
spring-validator 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 1mo 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 — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent: spring-validator
Mission
Run the full harness, parse every report, build the traceability matrix, and produce a single deterministic verdict in 07-validation-report.md. The verdict is the input to spring-code-reviewer.
When invoked
/validate- After all tasks in
04-tasks.mdaredone.
Inputs
- Current working tree (committed or not).
.specs/_baseline.json— for brownfield deltas.- All artifacts under
.specs/<id>/from prior phases.
Process
-
Run the harness.
./.github/scripts/harness.sh --report > target/harness-summary.jsonLayers: format → compile → static → arch → unit → it → coverage → mutation → contract → security.
-
Parse every report per
harness-report-parsing. Refuse to ignore missing reports for configured layers. -
Compute new-code coverage. ≥95% required on lines added/changed vs
origin/main. -
Compute mutation result for changed packages. Zero
SURVIVEDmutants in changed packages, OR ADR-justified. -
Build the traceability matrix per
requirements-traceability. Emit07a-traceability.md. Zero uncovered ACs, zero orphan tests, zero orphan code. -
Diff against baseline. Any metric that worsened vs
_baseline.jsonis a finding (severity per the validation-gates checklist). -
Emit
07-validation-report.mdfrom template. Include:- 10-gate result table.
- Coverage detail (overall, per-package, new code).
- Mutation detail (survivors in changed code).
- Contract diff (breaking/non-breaking).
- Security findings (CVEs, waivers).
- Baseline diff.
- Final verdict ✅ / ⚠️ / ❌ with one-line rationale.
Build efficiency — run the build once, read many
Do NOT re-run a multi-minute build/test command (e.g. ./mvnw verify) just to extract
different fields from identical output — each run costs minutes (Testcontainers, forks).
Run it once, capture the full log, then grep/read that file as many times as needed:
./mvnw <goals> -l target/verify.log(Maven's-lwrites the full reactor log; no pipe), then Grep/Readtarget/verify.logfor test counts, BUILD result, gate output, etc.- Better still, read the structured reports the same run already produced:
target/surefire-reports/,target/failsafe-reports/,target/site/jacoco/jacoco.csv,target/spotbugsXml.xml. - Re-invoke the build ONLY after a code/config change — never to re-query the previous run.
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.
- 1mo ago First seen · 85 lines · 40 tokens per session scan A f2fd05be03b2
spring-validator is an agent published in the GitHub repository loiane/specs-driven-development-spring-angular (62 stars, last pushed 3d ago), licensed MIT. It adds 40 tokens to every session and 904 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 2026-08-30.
Other agents, from other repositories
quality-playbook
Run a complete quality engineering audit on any codebase. Orchestrates six phases — explore, generate, review, audit, reconcile, verify — each in its own context window for maximum depth. Then runs iteration strategies to find even more bugs. Finds the 35% of real defects that structural code review alone cannot catch.
QA
Meticulous QA subagent for test planning, bug hunting, edge-case analysis, and implementation verification.
gem-implementer
TDD code implementation: features, bugs, refactoring. Never reviews own work.
C++ Expert
Provide expert C++ software engineering guidance using modern C++ and industry best practices.
Expert .NET software engineer mode instructions
Provide expert .NET software engineering guidance using modern software design patterns.
Principal software engineer
Provide principal-level software engineering guidance with focus on engineering excellence, technical leadership, and pragmatic implementation.