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 code-reviewgit 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/code-review)<a href="https://agentmods.dev/skills/jstoup111/ai-conductor/code-review"><img src="https://agentmods.dev/badge/skills/jstoup111/ai-conductor/code-review/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/code-review"><img src="https://agentmods.dev/badge/skills/jstoup111/ai-conductor/code-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, 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 Excessive Agency · line 9 Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.
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 | $0.00032 | $0.01866 |
| Opus 5.5 | $0.00013 | $0.00746 |
| Sonnet 5.5 | $0.00006 | $0.00373 |
| Haiku 4.5 | $0.00003 | $0.00187 |
Grade A, and why
code-review 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 14d 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 — 185 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Purpose
Implements the generator/evaluator separation pattern. The evaluator gets a fresh context reset (no shared state with the generator) and is prompted for calibrated skepticism — finding real issues, not rubber-stamping work.
Correctness gate: a review finding is a claim, and a false-confident one either blocks good
work or waves through a bug. Per the /verify-claims protocol, the evaluator attaches a grounded
confidence % and its basis to each finding (verified — reproduced/traced in the code — vs
inferred), never asserts a defect it has not verified, and flags a low-confidence finding as
tentative rather than as a hard defect.
Provider-native delegation
Dispatch the evaluator through the selected host's available subagent facility. Preserve the fresh context boundary, skeptical review, verdict output, and blocking gates regardless of host. Claude delegation: Claude uses the Agent tool; the Claude model choices below apply only to that facility. A Codex-selected run uses its available subagent facility and configured Codex provider policy, without translating Claude model names.
Practices
1. Prepare Review Context
Gather what the evaluator needs:
- Git diff of changes — for batch reviews, scope to the current batch only (commits since
last batch boundary via
git diff <batch-start-commit>..HEAD), not the full branch diff. For the final batch, add a lightweight integration check (full branch diff stat summary) but do NOT re-review earlier batches line by line. - The story/acceptance criteria being implemented (from
.docs/stories/) - The implementation plan task (from
.docs/plans/) - The relevant affected-test result set
- Tech-context review checklist if loaded in session
- A focused current-HEAD pattern basis, when the task supplies one: current-checkout paths for the relevant target and exemplar, stable symbol or role hints, the semantic traits to preserve or change, and allowed variation. It complements the task criteria and affected-test results; it does not expand review context to the full plan, unrelated stories, or history.
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.
- 14d ago Changed 42d917db9682
- 1mo ago Changed 66696ef7b05a
- 1mo ago Changed · -2 lines ef9fd62e7ce7
- 1mo ago Changed · +5 lines 13d11d3a675f
- 2mo ago First seen · 182 lines · 32 tokens per session scan A db3b5d54ca0a
code-review is a skill published in the GitHub repository jstoup111/ai-conductor (7 stars, last pushed today), licensed Apache-2.0. It adds 32 tokens to every session and 1,866 once invoked, about $0.0001 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 2026-08-31.
Other skills, from other repositories
autoreview
Structured code review through the shared OpenClaw agent-skills installation.
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
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"…
explore-unknowns
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…
asplos-writing-style
Use when drafting or revising ASPLOS prose — engineering the first two pages that rapid review actually reads, stating the cross-layer insight as one quotable sentence, structuring per-layer mechanism sections, writing bounded claims, and fitting everything into 11 self-contained pages that include figures and…