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 dhslegen/digital-delivery-team --skill validation-loopgit clone --depth 1 https://github.com/dhslegen/digital-delivery-teamWrote 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/dhslegen/digital-delivery-team/validation-loop)<a href="https://agentmods.dev/skills/dhslegen/digital-delivery-team/validation-loop"><img src="https://agentmods.dev/badge/skills/dhslegen/digital-delivery-team/validation-loop/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/dhslegen/digital-delivery-team/validation-loop"><img src="https://agentmods.dev/badge/skills/dhslegen/digital-delivery-team/validation-loop.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 | $0.00053 | $0.01887 |
| Opus 5.5 | $0.00021 | $0.00755 |
| Sonnet 5.5 | $0.00011 | $0.00377 |
| Haiku 4.5 | $0.00005 | $0.00189 |
Grade A, and why
validation-loop scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
✓ smoke: curl http://localhost:3001/health 200 OK How it starts
The opening of the file, as written. The whole thing — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Validation Loop · 每步验证
Golden Rule: If a validation fails, fix it before moving on. Never accumulate broken state.
M6.4 整改：v0.6.x 的 backend-agent / frontend-agent 是写完才测， 一旦有 bug 已经写了 10 个文件，根因排查困难。 v0.7.0 改 main thread + validation loop——每文件立即测，失败立即停。
Triggers
/build-apiIMPLEMENT phase（每个 step 后）/build-webIMPLEMENT phase（每个组件后）/fix --apply（每条 patch 后）- 任何 main thread 写完一个关键文件后
Core Philosophy
不累积破损状态：每一步验证失败都立即停下，让用户决策是修复 / 跳过 / 重新规划。 不要"先写 10 个文件再一起测"——出问题时无法定位是哪步引入的。
检测包管理器与构建工具
按文件存在性自动选对命令：
| 检测到的文件 | 包管理器 | build 命令 | lint 命令 | typecheck 命令 | test 命令 |
|---|---|---|---|---|---|
pnpm-lock.yaml |
pnpm | pnpm run build |
pnpm run lint |
pnpm exec tsc --noEmit |
pnpm test --run |
yarn.lock |
yarn | yarn build |
yarn lint |
yarn tsc --noEmit |
yarn test --run |
package-lock.json 或 package.json 无 lock |
npm | npm run build |
npm run lint |
npx tsc --noEmit |
npm test --silent --run |
pom.xml |
maven | mvn -B compile |
mvn -B verify -DskipTests |
mvn -B compile |
mvn -B test |
build.gradle* |
gradle | ./gradlew build -x test |
./gradlew check -x test |
./gradlew compileJava |
./gradlew test |
pyproject.toml + poetry.lock |
poetry | poetry build |
poetry run ruff check |
poetry run mypy . |
poetry run pytest |
pyproject.toml 无 poetry |
pip + ruff | — | ruff check . |
mypy . |
pytest |
Cargo.toml |
cargo | cargo build |
cargo clippy |
cargo check |
cargo test |
go.mod |
go | go build ./... |
golangci-lint run |
go vet ./... |
go test ./... |
命令优先用项目脚本（如
npm run build）；脚本不存在则 fallback 到通用命令（tsc --noEmit）。
Validation Mode（按场景选）
Quick Mode（每个文件后）
只跑当前文件相关的最快验证：
.ts/.tsx：tsc --noEmit <path>+ 该文件 lint.js：<lint> <path>.java：当前模块mvn -B compile -pl <module>.go：go vet <package>+go build <package>.py：mypy <path>+ruff check <path>
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 · 166 lines · 53 tokens per session scan A e3b90169f829
validation-loop is a skill published in the GitHub repository dhslegen/digital-delivery-team (1 stars, last pushed 5mo ago), licensed MIT. It adds 53 tokens to every session and 1,887 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
completion-verification
Verifies that work is actually complete before it is claimed to be — running the checks, reading the output, and confirming the original request was satisfied rather than approximated. Use this before saying something is done, fixed, or passing; before committing or opening a pull request; and whenever a claim of…
proof-e2e
Build E2E test specs for critical user journeys — Playwright or Cypress, page objects, setup/teardown, CI config. Use when asked to "write E2E tests", "end-to-end testing", "browser tests", "UI tests", or "Playwright tests".
mean-tester
Mean test another agent when someone asks you to test, check or break it. Invoke on "test @agent", "mean test @agent", "check whether @agent works", on "continue " or "rerun " in a new message, or on "continue" in a thread where you already reported a campaign, and on "Judge this recorded exchange".
knowledge-wiki
A tool that turns useful lessons from coding sessions into general articles for a team wiki. A wiki is a collection of linked reference pages, and this one can be kept locally or shared through a Git repository.
design-system-reference
Style guides and implementation rules for frontend design. Works with design-discovery agent which handles context gathering and VS-based style recommendations. Contains detailed style guides, anti-patterns, and implementation checklists.
e2e
Orchestrates e2e testing: BDD scenarios, Playwright autotests. Triggers: e2e tests, BDD scenarios, write autotest.