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 racecraft-lab/racecraft-plugins-public --skill installgit clone --depth 1 https://github.com/racecraft-lab/racecraft-plugins-publicWrote 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/racecraft-lab/racecraft-plugins-public/install)<a href="https://agentmods.dev/skills/racecraft-lab/racecraft-plugins-public/install"><img src="https://agentmods.dev/badge/skills/racecraft-lab/racecraft-plugins-public/install.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to medium
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 →
- medium Rogue Agent · line 134 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
- medium Excessive Agency · line 200 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 203 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00054 | $0.03636 |
| Opus 5 | $0.00027 | $0.01818 |
| Sonnet 5 | $0.00011 | $0.00727 |
| Haiku 4.5 | $0.00005 | $0.00364 |
Grade A, and why
install 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 3d 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.
How it starts
The opening of the file, as written. The whole thing — 373 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SpecKit Install
Scope
Use this skill when the user wants to install, refresh, repair, or verify the Codex custom subagents that ship with this plugin. This skill exists only for the Codex runtime. It does not manage Claude Code agents, Claude marketplace metadata, or Claude commands.
The bundled source of truth lives in the plugin at:
codex-agents/*.toml
The default user-scope Codex destination is:
~/.codex/agents/
If the user explicitly asks for project scope, use .codex/agents/ in the
current project. Arbitrary destinations are rejected. Otherwise install to the
default user-scope path above.
What This Skill Installs
This skill installs the bundled TOML subagent templates that the Codex autopilot expects to exist as real custom subagents:
analyze-executor.tomlartifact-author.tomlautopilot-fast-helper.tomlchecklist-executor.tomlclarify-executor.tomlcodebase-analyst.tomldomain-researcher.tomlimplement-executor.tomlphase-executor.tomlspec-context-analyst.tomluat-runbook-author.toml
The bundled source inventory is strict: all 11 TOML files must be present
before the installer plans either static or route-aware destination changes.
In route-aware planning, 10 files are required destination agents and
autopilot-fast-helper.toml is the only optional helper. The main autopilot
may use that helper for tiny advisory text-only prep work when
gpt-5.6-luna is available, but autopilot must continue without it if
the helper is unavailable and no-helper continuation validates.
These files follow the official Codex subagent format: one standalone
TOML file per custom agent, with required name, description, and
developer_instructions fields plus Codex config such as model,
model_reasoning_effort, and sandbox_mode.
Operator note: on Codex, sandbox_mode = "read-only" does not sandbox
MCP server processes. The agent TOML cannot restrict tools, so to keep a
read-only agent provably unable to cause writes via MCP, the operator must
curate write-capable MCP servers OUT at the profile/config level (enabled = false, or enabled_tools/disabled_tools).
What ships with it
1 file 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.
- 3d ago First seen · 373 lines · 54 tokens per session scan A 96eac5d13235
install is a skill published in the GitHub repository racecraft-lab/racecraft-plugins-public (5 stars, last pushed yesterday), licensed MIT. It adds 54 tokens to every session and 3,636 once invoked, about $0.0003 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 2026-09-04.
Other skills, from other repositories
stay-within-limits
Use when long-running or parallel agent work must respect 5-hour and weekly usage limits by checking usage between waves, pausing near the cap, and resuming only when the window is clear.
gsd-ns-manage
Route to the appropriate management skill based on the user's intent. gsd-config (settings + advanced + integrations + profile) and gsd-workspace (new + list + remove) are post-#2790 consolidated entries.
obsidian-bases
Create and edit Obsidian Bases (.base files) with views, filters, formulas, and summaries. Use when working with .base files, creating database-like views of notes, or when the user mentions Bases, table views, card views, filters, or formulas in Obsidian.
workflow-start
Primary entry point for the spec-superflow state-machine workflow. Invoke when the user is inside an active spec-superflow change directory (look for .spec-superflow.yaml, changes/ /, proposal.md, specs/, design.md, tasks.md, or execution-contract.md) and asks to start, continue, resume, implement, plan, or figure out…
find-journalists
Build, refine, dedupe, and enrich small fit-checked journalist lists for newsjack campaigns. Uses the newsjack CLI (preferred) or the medialyst MCP for news search and journalist enrichment, and falls back to a best-effort local mode with no verified contacts; the agent owns how returned data is organized.
contract-builder
Convert approved planning artifacts into an execution contract. Invoke when the user wants to start building, asks to move from planning to implementation, or when execution-contract.md is missing or stale.