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 agentmods add skills/sorryorc/mcp-codex-worker/worker-external-positioningnpx skills add sorryorc/mcp-codex-worker --skill worker-external-positioninggit clone --depth 1 https://github.com/sorryorc/mcp-codex-workerWrote 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/sorryorc/mcp-codex-worker/worker-external-positioning)<a href="https://agentmods.dev/skills/sorryorc/mcp-codex-worker/worker-external-positioning"><img src="https://agentmods.dev/badge/skills/sorryorc/mcp-codex-worker/worker-external-positioning.svg" alt="Measured on agentmods" 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 | $0.00030 | $0.00280 |
| Opus 5 | $0.00015 | $0.00140 |
| Sonnet 5 | $0.00006 | $0.00056 |
| Haiku 4.5 | $0.00003 | $0.00028 |
Grade A, and why
worker-external-positioning 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 4d 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.
What it actually says
Worker External Positioning
Claim Rules
- The project is a harness and routing layer, not proof that cheap models are smart.
- Cost savings are credible only with metrics.
- Reliability claims require checks, receipts, trajectory evidence, or eval cases.
- Community anecdotes are leads, not proof.
- Alleged leaked prompt analyses, including the Zhihu Fable 5 breakdown, are secondary signals. Use them to discuss harness structure, skill distillation, policy placement, and tool boundaries; do not present their contents as official vendor contracts.
Positioning Frame
- Cheap model handles bulk work.
- Harness limits damage with scope, receipts, artifacts, and checks.
- Main Codex remains the final decision layer.
- Skills preserve project doctrine for weaker sessions.
- Large monolithic prompts are a warning sign for worker design: move stable doctrine into validated skills and keep runtime prompts small, scoped, and auditable.
When Not To Use
Do not use this for implementation details. Use worker-architecture-contract.
Verification
- Cite primary sources for external claims.
- Run local metrics before quoting project performance.
Provenance and maintenance
Revalidate market and model comparisons because they drift quickly.
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.
- 4d ago First seen · 36 lines · 30 tokens per session scan A 4a95e38f6208
worker-external-positioning is a skill published in the GitHub repository sorryorc/mcp-codex-worker (2 stars, last pushed 16d ago), licensed MIT. It adds 30 tokens to every session and 280 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 2026-08-31.
Other skills, from other repositories
cost-mode
Cost-conscious Claude Code mode. Reduces output tokens 40-70% and overall costs 30-60% by enforcing concise responses, smart model routing, and efficient workflow patterns. Keeps full technical accuracy. Activate with /cost-mode or "enable cost mode". Auto-triggers on mentions of budget, cost, tokens, or spending.
rulesync
Generates and syncs AI rule configuration files (.cursorrules, CLAUDE.md, copilot-instructions.md) across 20+ coding tools from a single source. Use when syncing AI rules, running rulesync commands, importing or generating rule files, or managing shared AI coding configurations.
establishing-project-context
Use when the user asks to establish shared project language, or project work exposes a conflicting, renamed, or deprecated domain term that needs active semantic modeling. Routine small tasks stay on the fast path.
loop
Full execution protocol for MODE: LOOP — the compound-engineering loop: brainstorm → plan → build → review → improve, iterating under defense-in-depth stop conditions with generator/critic separation, durable resumable state, and mandatory compounding learning capture. Loaded on demand by the architect when the loop…
restore-internals-seams-in-finally-blocks-after-each-test
When delegating a task affected by this skill, include.
loongsuite-pilot-insight
基于 LoongSuite Pilot / AI Coding Agent 日志生成事件洞察、组织洞察、数据质量、研发效能和 AI Native 使用类 SLS 报表时使用；包含 AI Coding 事件表语义，以及团队报表可选的部门维表、deptuser 组织关系、指标口径和公共 CTE，通常与 sls-dashboard-builder 一起使用。.