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 jnPiyush/AgentX --skill code-reviewgit clone --depth 1 https://github.com/jnPiyush/AgentXWrote 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/jnpiyush/agentx/code-review)<a href="https://agentmods.dev/skills/jnpiyush/agentx/code-review"><img src="https://agentmods.dev/badge/skills/jnpiyush/agentx/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/jnpiyush/agentx/code-review"><img src="https://agentmods.dev/badge/skills/jnpiyush/agentx/code-review.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 | $0.00027 | $0.01028 |
| Opus 5.5 | $0.00011 | $0.00411 |
| Sonnet 5.5 | $0.00005 | $0.00206 |
| Haiku 4.5 | $0.00003 | $0.00103 |
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 7d 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 — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Review
When to Use
Use this after code, config, infra, migration, or automation changes that can change shipped behavior. Review the author's source and non-test verification. For docs-only work verify claims, links and instruction behavior without inventing a code score. For exploit hunting, use the security-review specialist.
Prerequisites
No blanket language checklist is universal. Gather the issue or requirement, accepted design, changed files, and the repository's real build, test, lint, and security commands before scoring anything.
Rationalization Table
| Excuse | Response |
|---|---|
| "CI passed, so approval is safe." | Passing automation is evidence, not a substitute for reading the change. |
| "I need at least three findings." | Verified issues beat quotas. Zero findings is valid when the evidence is strong. |
| "It is only config, test, or script work." | Those surfaces can ship outages; review the whole executed path. |
| "I can refresh the timestamp and reuse the old score." | Fresh hashes and fresh evidence are required after every code change. |
Agent Value
This skill turns review into an evidence-first release gate. It routes the reviewer to exact scope, requires executed verification, and anchors approval to the repository rubric instead of style-only comments or model-brand prestige.
Decision Guide
- If only prose changes, verify claims and references. Prompts/instructions also require task-evaluation evidence and token measurements when changed.
- If the request is to find exploitable security flaws, use the security review path first.
- If behavior changed, review the implementation, tests, config, and operator surfaces together.
- If hashes changed after review, restart from scope capture and rescore.
Workflow
- Verify the issue, acceptance criteria, and approved design.
- Read the full relevant surface, not just a line quota: implementation, tests, config, migrations, scripts, and docs that define the behavior.
- Run relevant non-test checks only. Do not execute test or coverage suites, including through pre-review scripts. Use run-checklist.ps1 only when it matches the stack.
- Capture exact scope with
pwsh scripts/score-code-quality.ps1 -Mode Scope -Json. - Score the change against evaluation/rubrics/code-quality.md.
- Approve only when the report still matches current hashes and no HIGH or MEDIUM findings remain.
What ships with it
4 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.
- 7d ago Changed · +9 lines 08da9c5debb9
- 1mo ago Changed · -159 lines · -20 tokens per session 9c78a4f0a64c
- 1mo ago First seen · 254 lines · 47 tokens per session scan A fabc5faa35e7
code-review is a skill published in the GitHub repository jnPiyush/AgentX (16 stars, last pushed 3d ago), licensed Apache-2.0. It adds 27 tokens to every session and 1,028 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 2026-09-03.
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"…
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…
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…