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 ryanczak/rexyMCP --skill reviewgit clone --depth 1 https://github.com/ryanczak/rexyMCPWrote 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/ryanczak/rexymcp/review)<a href="https://agentmods.dev/skills/ryanczak/rexymcp/review"><img src="https://agentmods.dev/badge/skills/ryanczak/rexymcp/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/ryanczak/rexymcp/review"><img src="https://agentmods.dev/badge/skills/ryanczak/rexymcp/review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
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 →
- high Rogue Agent · line 31 Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.Fix: Prevent the skill from modifying its own code, SKILL.md, or configuration files. Treat skill files as read-only at runtime.
- medium Excessive Agency · line 6 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 | $0.00033 | $0.02924 |
| Opus 5 | $0.00016 | $0.01462 |
| Sonnet 5 | $0.00007 | $0.00585 |
| Haiku 4.5 | $0.00003 | $0.00292 |
Grade A, and why
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 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 — 262 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review Skill
This skill is the substantive review gate. It re-runs the project's
commands, walks the Definition of Done from STANDARDS.md, spot-checks
tests, and either writes the Review verdict (flip to done) or files a bug
(flip back to in-progress). It does not execute the phase itself — that is
the executor's job. On hard_fail or budget_exceeded results, it delegates
to /rexymcp:escalate rather than reviewing.
Read these first
Before any action:
- Read the phase doc (resolve
<phase>from the argument). ItsStatus:line must bereview. If it istodo,in-progress, ordone, stop and tell the user the phase is not in a reviewable state. - Read
<repo>/docs/dev/STANDARDS.md— the Definition of Done checklist (§1) is what you verify against. - Read the milestone README (
docs/dev/milestones/M<n>-<slug>/README.md) for the phase table — status must mirror the phase doc. - Read the returned
PhaseResult. If the dispatch skill passed it in context, use that. If not available, query viaexecutor_log_tail+get_turnMCP tools using the phase'slog_pathfromrexymcp.toml.
The repo root is <repo> — resolve it from CLAUDE_PROJECT_DIR, ANTIGRAVITY_PROJECT_DIR, or the
nearest directory containing the milestone layout.
1. Refuse non-review-status phases
If the phase doc's Status: line is not review, stop. Tell the user:
"This phase is not in review status (current status: <actual>). It must
be reviewed by the executor first — re-dispatch via /rexymcp:dispatch <phase> if it is still todo."
2. Refuse hard_fail / budget_exceeded / cancelled results
Check PhaseResult.status:
- If
"hard_fail"or"budget_exceeded": this is an escalation, not a review. Point the user at/rexymcp:escalate <phase>and stop. Do not attempt to review partial work. - If
"cancelled": the run was deliberately stopped mid-phase (rexymcp stoporstop_phase) — its work is partial and the tree is dirty, so it is not reviewable. Point the user at/rexymcp:escalate <phase>(to resume the partial work) or a fresh re-dispatch, and stop. - If
"complete": proceed to §3.
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 · 262 lines · 33 tokens per session scan A 1b5faf4245fd
review is a skill published in the GitHub repository ryanczak/rexyMCP (86 stars, last pushed 22d ago), licensed MIT. It adds 33 tokens to every session and 2,924 once invoked, about $0.0002 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
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.
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.
include-test-files-that-assert-on-behavior-being-changed-in-decl
When delegating a task affected by this skill, include.
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…
plugin-review
Review plugin quality with tiered checks and dependency scoping. Use for PR and pre-release audits.