ardanlabs/service is a Go starter kit for building scalable web services designed to run in Kubernetes. It provides an organized starting structure based on domain-driven and data-oriented architecture, Go practices, and a small dependency set. The catalogue skills and instruction help coding agents work with services built from this starter kit.
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/ardanlabs/servicenpx agentmods add skills/ardanlabs/service/review-prWrote 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/ardanlabs/service/review-pr)<a href="https://agentmods.dev/skills/ardanlabs/service/review-pr"><img src="https://agentmods.dev/badge/skills/ardanlabs/service/review-pr/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/ardanlabs/service/review-pr"><img src="https://agentmods.dev/badge/skills/ardanlabs/service/review-pr.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Prompt Injection · line 22 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 53 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
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 | $0.00088 | $0.02180 |
| Opus 5 | $0.00044 | $0.01090 |
| Sonnet 5 | $0.00018 | $0.00436 |
| Haiku 4.5 | $0.00009 | $0.00218 |
Grade A, and why
review-pr 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 9d 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 — 180 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Service Diffguard
Service Diffguard reviews a diff with six focused lenses. Each lens runs as a read-only Amp Task subagent, inspects the requested change, and returns findings graded on one shared scale. Lenses advise only — they never edit, stage, or commit code, never disable tests, and never bypass a failing check to make it pass.
Default scope is the unstaged git diff unless the caller names specific
files, a branch, a commit range, or an existing PR.
Gate scale
Every finding carries a Gate. The run's overall Gate is the highest any lens returns.
| Gate | Name | Meaning | Action |
|---|---|---|---|
| G4 | Stop | Likely correctness, security, data-integrity, compile, boundary, or reliability failure. | Block merge until fixed. |
| G3 | Repair | Likely user-visible bug, operational blind spot, real test gap, or misleading contract. | Fix before the PR is ready. |
| G2 | Tighten | Locally safe but leaves avoidable risk, ambiguity, weak design, or brittleness. | Address if reasonably scoped; otherwise acknowledge. |
| G1 | Polish | Low-risk clarity, naming, comment, or small test refinement. | Optional; batch, don't spam. |
| G0 | Clear | No issue, or a positive observation. | None. |
Every G2 or higher finding must include: file:line, Proof (evidence from
the diff), why it matters, a Patch direction (smallest safe fix), and how to
verify. Weak or speculative observations go under Open checks, not as a
finding. Cap G1 items at five per lens unless exhaustive polish is requested.
What ships with it
6 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.
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.
- 9d ago First seen · 180 lines · 88 tokens per session scan A cb5fb9a85101
review-pr is a skill published in the GitHub repository ardanlabs/service (4,110 stars, last pushed 10d ago), licensed Apache-2.0. It adds 88 tokens to every session and 2,180 once invoked, about $0.0004 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 2026-08-30.
Other skills, from other repositories
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…