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/rbutera/harness-bridge/codexnpx skills add rbutera/harness-bridge --skill codexgit clone --depth 1 https://github.com/rbutera/harness-bridgeWrote 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/rbutera/harness-bridge/codex)<a href="https://agentmods.dev/skills/rbutera/harness-bridge/codex"><img src="https://agentmods.dev/badge/skills/rbutera/harness-bridge/codex.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 | $0.00027 | $0.00574 |
| Opus 5 | $0.00014 | $0.00287 |
| Sonnet 5 | $0.00005 | $0.00115 |
| Haiku 4.5 | $0.00003 | $0.00057 |
Grade A, and why
codex 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
You are invoking Codex to get a second opinion. Route the user's request to the most appropriate Codex MCP tool.
Tool Selection
Pick the best tool based on the user's request:
| Request Type | Tool | Key Parameters |
|---|---|---|
| Code review, diff review | mcp__codex__codex_review_code |
target (diff range or file), focusAreas |
| Plan critique | mcp__codex__codex_review_plan |
plan, codebasePath |
| Explain code | mcp__codex__codex_explain_code |
target (file/function), depth |
| Performance analysis | mcp__codex__codex_plan_perf |
target, metrics |
| Implement/fix (writes code) | mcp__codex__codex_implement |
task |
| General question | mcp__codex__codex_query |
prompt |
Instructions
- Parse the user's argument to determine the task type
- If the user references files, read them first for context
- Call the most specific Codex tool — prefer specialized tools over
codex_query - Always pass
workingDirectoryto every tool call - Synthesize the response: summarize key findings, highlight important points, give actionable recommendations
- Only use
codex_implementif the user explicitly asks Codex to make changes
Examples
/codex review my recent changes→codex_review_codewith target "HEAD~1..HEAD"/codex explain src/lib/exec.ts→codex_explain_codewith target "src/lib/exec.ts"/codex is my approach to caching correct?→codex_querywith the question/codex optimize the response parsing→codex_plan_perfwith target/codex implement error handling for timeouts→codex_implementwith task
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 · 39 lines · 27 tokens per session scan A 03b4ef30d786
codex is a skill published in the GitHub repository rbutera/harness-bridge (1 stars, last pushed 8d ago), licensed MIT. It adds 27 tokens to every session and 574 once invoked, about $0.0001 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
trusty-squire
Use when a coding agent needs to sign up for a website or SaaS, provision an OAuth client or API key, pay a checkout, or otherwise act on a real website on the user's behalf — and the secret or card must NOT land in chat, source code, or a .env file. Trusty Squire is an MCP server that drives a real browser through…
idesense
Guide for using JetBrains IdeSense tools for code navigation and analysis (plus the retained rename/move refactorings). TRIGGER: When ANY of these MCP tools are available in the current session: idefindusages, idefinddefinition, idefindclass, idefindfile, idesearchtext, idediagnostics, ideexplainsymbol…
internal-rag
Mandatory persistent project memory for substantial coding tasks. Use at task start, recovery, milestones, failures, before risky operations, before compaction, and before finishing. v1.0.1 adds type filtering, type-priority scoring, query expansion, grouped context output, and promote workflow.
identityforge
Use Identity Forge to choose, inspect, apply, or evolve a complete design system; create brand projects; research names, domains, or EUIPO trademarks; and retrieve implementation-ready DESIGN.md guidance and tokens.
Session Handoff
Preserve and resume coding-session context with Session Handoff. Use at the start of repository work, before clearing context, before handoff, or when completing a spec or substantial stage.
contextlock
Safely inspect a repository through the ContextLock MCP server. Use when exploring, searching, reviewing, or auditing repository files with ContextLock, especially before reading unfamiliar code or when sensitive files and secrets may be present.