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 jstoup111/ai-conductor --skill build-review-test-qualitygit clone --depth 1 https://github.com/jstoup111/ai-conductorWrote 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/jstoup111/ai-conductor/build-review-test-quality)<a href="https://agentmods.dev/skills/jstoup111/ai-conductor/build-review-test-quality"><img src="https://agentmods.dev/badge/skills/jstoup111/ai-conductor/build-review-test-quality/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/jstoup111/ai-conductor/build-review-test-quality"><img src="https://agentmods.dev/badge/skills/jstoup111/ai-conductor/build-review-test-quality.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00021 | $0.01839 |
| Opus 5 | $0.00010 | $0.00920 |
| Sonnet 5 | $0.00004 | $0.00368 |
| Haiku 4.5 | $0.00002 | $0.00184 |
Grade A, and why
build-review-test-quality 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 today.
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 — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Purpose
Judge the Test Quality concern for one engine-managed build_review rubric branch. This is a
judgement-only contract: the engine owns scope selection, evidence assembly, result validation,
finding identity, the stamped result envelope, and the outer gate verdict.
Input projection (v3)
Use only the supplied projection version v3. Its closed input contains:
- the lap ID, snapshot digest, and top-level
contentDigest; - the in-scope changed tests: only changed tests with a current-feature-owned, resolvable
Covers:binding introduced or updated after the review base, pointing to an approved story criterion, an active feature requirement (FR-N), or a taskDone when:check, represented as immutable content-region references; - the changed diff by reference (
changedFiles: per-file path, change kind, and hunk ranges), anchored bymergeBaseandheadSha; - the current code-valid
test_suitePASS; and - typed reverted-production preflight evidence, including its source identities, classification, scoped-run result, executed selectors, and bounded failure excerpt when applicable.
- any concrete fallback candidates in
testScope, each with its engine-established candidate ID, pinned source region, and allowed Covers obligation references. Unchanged legacy bare markers are excluded before projection; their ordinals never gain authority from the active plan.
The session runs inside the feature worktree. The diff content is not embedded: read referenced
files and obtain any per-path diff with git diff <mergeBase>..HEAD -- <path> (or the merge-base
form with git show <mergeBase>:<path>). Those reads are part of this closed input. Do not infer
facts from a maker transcript, task-status narrative, prior review, or state outside this projection
and its referenced content.
Judgement
For each in-scope changed test, judge whether its assertion actually distinguishes the behavior its
Covers: binding names. Raise test-insensitive only when the test has a concrete,
stub-passable assertion: it could pass while the changed behavior is absent or replaced with a
stub. Keep independent tests or behaviors as separate findings.
What ships with it
1 file 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.
- today Changed · +2 lines 63e883791f53
- yesterday Changed · +7 lines 6a3fe863f63a
- 2d ago Changed · +33 lines b5f92b1f690b
- 7d ago Changed · +35 lines 324317be9050
- 11d ago First seen · 75 lines · 21 tokens per session scan A 145fc7eb860f
build-review-test-quality is a skill published in the GitHub repository jstoup111/ai-conductor (7 stars, last pushed today), licensed Apache-2.0. It adds 21 tokens to every session and 1,839 once invoked, about $0.0001 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 skills, from other repositories
adversarial-reviewer
Adversarial code review that assumes bugs exist and hunts for them. Use when asked to review code, find bugs, audit for correctness, stress-test a PR, or when someone says "tear this apart" or "what's wrong with this". Give no benefit of the doubt — every line is guilty until proven innocent.
adk-go-self-review
Review an ADK Go change the way a maintainer will — a fresh-context pass over the whole diff, five lenses (correctness and tests, scope, simplicity, style, adk-python parity), and the mutation check that proves your tests pin the change. Use before opening a PR, before any later push that changes code, and when asked…
go-testing
Trigger: Go tests, go test coverage, Bubbletea teatest, golden files. Apply focused Go testing patterns.
semgrep-rule-variant-creator
Creates language variants of existing Semgrep rules. Use when porting a Semgrep rule to specified target languages. Takes an existing rule and target languages as input, produces independent rule+test directories for each language.
brooks-sweep
Full-sweep mode: runs a unified analysis across all quality dimensions — code decay, architecture, tech debt, and test quality — then applies fixes directly to the codebase. Safe changes are auto-applied; risky changes are confirmed before execution. Drawing on twelve classic engineering books. Triggers when: user…
include-test-files-that-assert-on-behavior-being-changed-in-decl
When delegating a task affected by this skill, include.