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/bengous/claude-code-plugins/codexnpx skills add bengous/claude-code-plugins --skill codexgit clone --depth 1 https://github.com/bengous/claude-code-pluginsWhat 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 | $0.00013 | $0.02270 |
| Opus 5 | $0.00006 | $0.01135 |
| Sonnet 5 | $0.00003 | $0.00454 |
| Haiku 4.5 | $0.00001 | $0.00227 |
Grade B, and why
codex 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 yesterday.
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.
Configured default (`~/.codex/config.toml`): How it starts
The opening of the file, as written. The whole thing — 187 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Codex Bridge
Invoke the OpenAI Codex CLI for a second opinion from a non-Claude model. The
scripts/codex wrapper is a thin pass-through that auto-installs the CLI via
npx on first use (requires node/npx on PATH, or mise). Pass codex's own
flags directly; the wrapper forwards everything.
The wrapper pins the CLI version (24 h TTL, falls back to the last working
install if npm breaks). AGENTS_BRIDGE_CODEX_VERSION=<x.y.z> freezes it
explicitly — the only env var the wrapper reads; everything codex-native goes
through codex's own flags.
Models
Configured default (~/.codex/config.toml):
!grep -E '^(model|model_reasoning_effort)' ~/.codex/config.toml 2>/dev/null || echo "(no ~/.codex/config.toml — codex uses its built-in default; the active model is printed in every 'exec' run header)"
Models the installed CLI accepts right now:
<codex_available_models>
# Live model list, injected once at skill load (~0.1 s).
# visibility != "list" hides codex-internal models (auto-review, reserve).
# Two constraints from the injected-command permission check:
# - No brace near a quote anywhere in this block, comments included: that
# is "expansion obfuscation", and allowed-tools cannot override it. Hence
# + concatenation in jq. CLAUDE_PLUGIN_ROOT is substituted before the check.
# - The allowed-tools Bash rule must match the codex call: Bash(*) does,
# Bash(*:*) does not (it reads as a literal-star prefix).
# Never exit non-zero: a failed injected command aborts the whole skill.
"${CLAUDE_PLUGIN_ROOT}/scripts/codex" debug models 2>/dev/null |
jq -r '.models[]
| select(.visibility == "list")
| .slug + " | default effort: " + .default_reasoning_level
+ " | efforts: " + ([.supported_reasoning_levels[].effort] | join(","))
+ " | " + .description' || true
</codex_available_models>
Pass a slug from that block, never a name from training data. An empty block
means the CLI was unreachable: pass no -m and let the configured default run.
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.
- yesterday First seen · 187 lines · 13 tokens per session scan B 1f93b8f11d49
codex is a skill published in the GitHub repository bengous/claude-code-plugins (4 stars, last pushed 2d ago), licensed MIT. It adds 13 tokens to every session and 2,270 once invoked, about $0.0001 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 2026-08-31.
Other skills, from other repositories
sql-reporting
Conventions and review steps for writing analytics SQL against the warehouse. Use whenever the task involves querying tables, building a report, or aggregating metrics.
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
verify-security
安全校验关卡。自动扫描代码安全漏洞，检测危险模式，确保安全决策有文档记录。当用户提到安全扫描、漏洞检测、安全审计、代码安全、OWASP、注入检测、敏感信息泄露时使用。在新建模块、安全相关变更、攻防任务、重构完成时自动触发。.
development
开发语言能力索引。Python、Go、Rust、TypeScript、Java、C++、Shell。当用户提到编程、开发、代码、语言时路由到此。.
post-build-flow
Handles workflow verification and setup after build-workflow succeeds, or when the message contains workflow-verification-follow-up or workflow-setup-required. Load after direct builds, when verificationReadiness requires action, or on orchestrator verify/setup follow-up turns.
n8n:human-like-code-review
Reviews a GitHub pull request like a thoughtful human reviewer and writes the feedback to a markdown file. Prioritizes context, architecture fit, solution complexity, bugs, security edge cases, and missing tests. Use when given a PR URL to review, or when the user says /human-like-code-review.