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 cboone/agent-harness-plugins --skill set-up-review-configgit clone --depth 1 https://github.com/cboone/agent-harness-pluginsWrote 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/cboone/agent-harness-plugins/set-up-review-config)<a href="https://agentmods.dev/skills/cboone/agent-harness-plugins/set-up-review-config"><img src="https://agentmods.dev/badge/skills/cboone/agent-harness-plugins/set-up-review-config/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/cboone/agent-harness-plugins/set-up-review-config"><img src="https://agentmods.dev/badge/skills/cboone/agent-harness-plugins/set-up-review-config.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 | $0.00039 | $0.02897 |
| Opus 5.5 | $0.00016 | $0.01159 |
| Sonnet 5.5 | $0.00008 | $0.00579 |
| Haiku 4.5 | $0.00004 | $0.00290 |
Grade A, and why
set-up-review-config 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 15d 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.
1. With a pin, check that the bundled checklists are current. For each guide, fetch `https://raw.githubusercontent.com/cboone/agent-harness-plugins/<sha>/plugins/<guide>/skills/<guide>/references/review-checklist.md` wit How it starts
The opening of the file, as written. The whole thing — 118 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Set-Up Review Config
Install review guidance that three automated pull request reviewers read, built from the style guides in this marketplace:
| Reviewer | Reads | Installed |
|---|---|---|
| Copilot code review | Skills under .github/skills/; a skill directory named code-review is always used |
.github/skills/code-review/SKILL.md, which routes each changed file to its checklist |
| Codex cloud review | ## Code Review Rules sections in AGENTS.md |
A managed block in that section of the root AGENTS.md |
| Claude Code Review | The root REVIEW.md, plus CLAUDE.md as nit-level context |
A managed block in REVIEW.md, including every checklist's Important rules |
The checklists are bundled in ./references/checklists/, one per style guide, and are installed verbatim beside the entry SKILL.md. Every rule has a bold name, and findings cite it as <guide>: <rule name>, for example write-go-code: Checked errors.
Options
- --dry-run: Detect, then present the plan in step 5 and stop without writing anything.
Managed Content
- Blocks: A managed block starts with a line holding exactly
<!-- BEGIN set-up-review-config -->and ends with a line holding exactly<!-- END set-up-review-config -->, with one blank line after the first and one before the second. A rerun replaces everything from the BEGIN line through the END line, and nothing else. - Whole files: An installed checklist file is managed as a whole. Its first line is a comment that begins
<!-- Managed by set-up-review-config. A file without that first line is never overwritten or removed. - Precedence: Everything outside the managed blocks belongs to the repository. The blocks say that rules outside them take precedence, so exceptions and repository-specific checks go there.
- Format: The templates avoid tables,
*bullets and other constructs that Markdown formatters rewrite, so a formatted file still matches what a rerun writes.
What ships with it
10 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.
- references/agents-md-section.md 1.4 KB
- references/checklists/write-bash-scripts.md 4.1 KB
- references/checklists/write-go-code.md 4.3 KB
- references/checklists/write-lean-code.md 4.7 KB
- references/checklists/write-markdown.md 2.6 KB
- references/checklists/write-scrut-tests.md 2.7 KB
- references/checklists/write-zsh-scripts.md 4.2 KB
- references/code-review-skill.md 4.2 KB
- references/guides.md 4.1 KB
- references/review-md.md 2.9 KB
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.
- 15d ago Changed · +1 lines 96eff4b6a4a5
- 25d ago First seen · 117 lines · 39 tokens per session scan A 1cdf9b448a1e
set-up-review-config is a skill published in the GitHub repository cboone/agent-harness-plugins (2 stars, last pushed yesterday), licensed MIT. It adds 39 tokens to every session and 2,897 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 2026-09-21.
Other skills, from other repositories
review-pr
Review a pull request for conceptual fit, architecture impact, adversarial failure modes, security risk, docs impact, regression risk, test coverage, and merge readiness. Use when asked to review a PR, check whether a PR is safe to merge, decide if more tests are needed, perform adversarial or security review, or…
software-code-refactoring
Improve production code quality while preserving all existing test behavior. Commonly used for the Refactor phase of TDD red-green-refactor, but applicable to any codebase with tests. Use when production code works but needs cleanup — reducing duplication, improving naming, simplifying complexity, aligning with…
drift-check
Pre-PR advisory check for deviations from the project spec. Read-only analysis.
review-preflight
Review tooling for a PR: review-preflight prints REVIEW.md's criteria and the PR's live gate state before a review; ci-triage maps a PR's failing checks to already-filed issues.
remarc
Manage Remarc session comments and contextual feedback. Use when the user mentions Remarc sessions, comments, handoff, triage, review, addressing, resolving, status updates, or summaries.
fuck-over-engineering
Use when the user asks what could be deleted or reduced to simplify a codebase, says "simplify", "over-engineered", or wants a repo-, folder-, or file-wide audit for over-engineering — hunts dead code, reinvented stdlib, needless dependencies, and single-implementation abstractions, reports ranked cuts, applies only…