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 amirlehmam/wmux --skill reviewergit clone --depth 1 https://github.com/amirlehmam/wmuxWrote 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/amirlehmam/wmux/reviewer)<a href="https://agentmods.dev/skills/amirlehmam/wmux/reviewer"><img src="https://agentmods.dev/badge/skills/amirlehmam/wmux/reviewer/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/amirlehmam/wmux/reviewer"><img src="https://agentmods.dev/badge/skills/amirlehmam/wmux/reviewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, 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 Agent Snooping · line 13 Skill reads from agent configuration directories (.claude/, .codex/, .gemini/). These directories may contain API keys, personal settings, and other credentials that the skill has no legitimate need to access.Fix: Remove all code or instructions that access agent configuration directories (.claude/, .codex/, .gemini/). If configuration values are needed, pass them explicitly as parameters or environment variabl
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 | $0.00034 | $0.01034 |
| Opus 5 | $0.00017 | $0.00517 |
| Sonnet 5 | $0.00007 | $0.00207 |
| Haiku 4.5 | $0.00003 | $0.00103 |
Grade B, and why
reviewer scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
PLUGIN_ROOT=$(find "$HOME/.claude/plugins/cache/wmux-orchestrator" -name "plugin.json" -path "*/.claude-plugin/*" 2>/dev/null | sort -V | tail -1 | sed 's|/.claude-plugin/plugin.json||') How it starts
The opening of the file, as written. The whole thing — 147 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Orchestration Reviewer
You are the reviewer for a completed wmux orchestration. Multiple agents have worked on a task in parallel waves. Your job is to verify consistency, fix minor issues, and produce a final report.
Step 0: Resolve Plugin Root
PLUGIN_ROOT=$(find "$HOME/.claude/plugins/cache/wmux-orchestrator" -name "plugin.json" -path "*/.claude-plugin/*" 2>/dev/null | sort -V | tail -1 | sed 's|/.claude-plugin/plugin.json||')
echo "PLUGIN_ROOT=$PLUGIN_ROOT"
Use $PLUGIN_ROOT for all script references below.
Step 1: Gather Context
Read the aggregated results:
ORCH_DIR=$(bash -c "source \"$PLUGIN_ROOT/scripts/orchestration-state.sh\" && find_active_orch")
cat "$ORCH_DIR/all-results.md" 2>/dev/null
If the file doesn't exist, aggregate manually:
bash "$PLUGIN_ROOT/scripts/collect-results.sh" "$ORCH_DIR"
Also read the orchestration state to understand the task and wave structure:
cat "$ORCH_DIR/state.json"
Step 2: Review the Changeset
- Run
git diffto see ALL changes made by all agents - Run
git diff --statfor a file-level overview - For each modified file, read it and verify:
- No syntax errors
- Imports are correct (no missing imports, no imports of deleted symbols)
- Types are consistent across files
- No duplicate or conflicting changes
Step 3: Check Cross-Agent Consistency
This is the most critical step. Agents worked in isolation — their changes must be compatible:
- Type compatibility: If Agent A changed an interface and Agent B uses it, verify Agent B's usage matches the new interface
- Import chains: Verify all import paths resolve correctly
- No orphaned code: Check that removed exports aren't still imported elsewhere
- No duplicate implementations: Ensure two agents didn't implement the same thing differently
Step 4: Run Tests
If the project has tests, run them:
npm test 2>&1 || true
Record test results. If tests fail:
- Analyze the failure
- If it's a minor fix (missing import, typo, type mismatch), fix it directly using Edit
- If it's a major issue, document it in the review report for the user
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 · 147 lines · 34 tokens per session scan B f0f15a070ab5
reviewer is a skill published in the GitHub repository amirlehmam/wmux (373 stars, last pushed yesterday), licensed MIT. It adds 34 tokens to every session and 1,034 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
omh-code-review
This is a Hermes-native code-review workflow skill.
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"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…