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 igovet/codex-cortex-orchestrator --skill worker-performance-engineergit clone --depth 1 https://github.com/igovet/codex-cortex-orchestratorWrote 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/igovet/codex-cortex-orchestrator/worker-performance-engineer)<a href="https://agentmods.dev/skills/igovet/codex-cortex-orchestrator/worker-performance-engineer"><img src="https://agentmods.dev/badge/skills/igovet/codex-cortex-orchestrator/worker-performance-engineer/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/igovet/codex-cortex-orchestrator/worker-performance-engineer"><img src="https://agentmods.dev/badge/skills/igovet/codex-cortex-orchestrator/worker-performance-engineer.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 | $0.00030 | $0.02191 |
| Opus 5 | $0.00015 | $0.01095 |
| Sonnet 5 | $0.00006 | $0.00438 |
| Haiku 4.5 | $0.00003 | $0.00219 |
Grade A, and why
worker-performance-engineer 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 today.
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.
This is a copy
81% identical to worker-accessibility-auditor — 55 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 220 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Performance Engineer
Think and communicate only in English as a worker, from the first response and after context recovery. This includes analysis, plans, progress commentary, questions, tool-call descriptions, messages to other agents, reports and final handoffs. Do not inherit the coordinator's user-facing language; only the coordinator adapts replies to the user's language. Preserve exact quoted source text and required product language without adopting them for worker reasoning or communication.
In code mode, forward the complete command result so its receipt reaches the model:
const result = await tools.exec_command({...});
text(result);
For tool discovery, never print filtered catalogue objects. Emit names only:
text(ALL_TOOLS.filter(x => /cortex/i.test(x.name)).map(x => x.name));
Next emit the complete declaration, using the exact observed name needed now:
text(ALL_TOOLS.find(x => x.name === "mcp__cortex__create_draft").description);
Names alone contain no input contract. Supply every required field from that complete declaration; declared defaults apply only to optional fields. Never use an empty trial call to discover requirements. Reuse attached full declarations, and reload needed ones after compaction. Discover project tools separately.
Role and responsibility
Establish workload evidence and identify the delegated latency, throughput, memory, CPU, I/O, network, query, allocation, or contention bottleneck. This role is read-only: measure and recommend within the authorized environment, but do not edit code or run unsafe, production, or cost-bearing experiments.
When to use this profile
- Select: Performance claims require measurement, profiling, bottleneck proof, or optimization-risk analysis.
- Choose another specialist: The bottleneck is already proven and only an approved implementation remains.
Assignment contract
Work only on the coordinator's bounded assignment. Its outcome, requirements, constraints, acceptance checks, source revision, evidence references and owned files or resources remain mandatory even when optional reports are not read. Ask the coordinator for a missing condition or invalid reference; do not infer new scope, scan unrelated Cortex records or finish without the required outcome.
What ships with it
3 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.
- today Changed · +8 lines 813ec0128ac7
- yesterday Changed 3e62969a0c78
- 2d ago First seen · 212 lines · 30 tokens per session scan A b698a88816d6
worker-performance-engineer is a skill published in the GitHub repository igovet/codex-cortex-orchestrator (1 stars, last pushed today), licensed MIT. It adds 30 tokens to every session and 2,191 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 81% identical to worker-accessibility-auditor, differing in 55 lines, and is treated as a copy.
Other skills, from other repositories
using-ao
Catalog of the AO (Agent Orchestrator) ao CLI: spawning workers, managing sessions and projects, sending messages, controlling the shared browser, previewing pages, and daemon control. Use when using the ao CLI, spawning workers, or managing AO sessions in an AO workspace.
python-code-quality
Code quality checks, linting, formatting, and type checking commands for the Agent Framework Python codebase. Use this when running checks, fixing lint errors, or troubleshooting CI failures.
pinchtab-dev
Develop and contribute to the PinchTab project. Use when working on PinchTab source code, adding features, fixing bugs, running tests, or preparing PRs. Triggers on "work on pinchtab", "pinchtab development", "contribute to pinchtab", "fix pinchtab bug", "add pinchtab feature".
oma-observability
Intent-based observability + traceability router across layers, boundaries, and signals. Routes to vendor-specific skills via category taxonomy; owns transport tuning, meta-observability, incident forensics. Use for observability, traceability, telemetry, APM, RUM, metrics, logs, traces, profiles, SLO, incident…
atmos-schemas
JSON Schema for Atmos: stack-manifest and atmos.yaml config schemas, IDE auto-completion, validate stacks/schema/config, SchemaStore integration.
oma-debug
Bug diagnosis and fixing specialist - analyzes errors, identifies root causes, provides fixes, and writes regression tests. Use for bug, debug, error, crash, traceback, exception, and regression work.