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 richkuo/rk-skills --skill cli-dispatchgit clone --depth 1 https://github.com/richkuo/rk-skillsWrote 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/richkuo/rk-skills/cli-dispatch)<a href="https://agentmods.dev/skills/richkuo/rk-skills/cli-dispatch"><img src="https://agentmods.dev/badge/skills/richkuo/rk-skills/cli-dispatch/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/richkuo/rk-skills/cli-dispatch"><img src="https://agentmods.dev/badge/skills/richkuo/rk-skills/cli-dispatch.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
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 →
- high Excessive Agency · line 34 Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.
- medium Rogue Agent · line 23 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.
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 | $0.00101 | $0.02346 |
| Opus 5 | $0.00051 | $0.01173 |
| Sonnet 5 | $0.00020 | $0.00469 |
| Haiku 4.5 | $0.00010 | $0.00235 |
Grade A, and why
cli-dispatch scanned grade A 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 5d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- `-s workspace-write` keeps Codex writes inside the repository; `sandbox_workspace_write.network_access=true` lets `git push` and `gh` reach the network. A 2026-09-02 smoke run (codex-cli 0.152.1, `gpt-5.6-luna`, this f How it starts
The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLI dispatch
How a build reaches the Codex CLI or the Cursor CLI when an issue stamps Build model: <Name> (Codex CLI) or <Name> (Cursor CLI). The caller owns the task prompt and the result; this skill owns the path to the CLI. A run on a model other than the stamped one is a substitution: always reported, never presented as the stamped build. This procedure never falls back to a Claude build: the stamp is a user override, and a silent fallback is the defect this skill closes.
1. Preflight
Check only the CLI the stamp names, before writing any file: command -v codex && codex login status or command -v agent && agent status. A missing binary or a signed-out status blocks that issue (name the binary or the login); the caller runs the rest of the milestone.
2. Model id and effort
Luna (Codex CLI)resolves togpt-5.6-luna;Grok (Cursor CLI)resolves tocursor-grok-4.6-<effort>. An explicit id in the parenthetical (Luna (Codex CLI, gpt-5.6-luna)) is used verbatim. Any other name with no explicit id is a blocker; never guess an id.- Codex tiers
low,medium,high,xhigh,maxpass as-c model_reasoning_effort=<tier>. Cursor encodes the tier in the id suffix; the caller normalizesmaxtoxhighwith a log line. agent --list-modelsprints the ids Cursor accepts (agentandcursor-agentare one binary); run it when an explicit id looks unfamiliar. On 2026-09-02 (cursor-agent 2026.09.02) it listedcursor-grok-4.6-{low,medium,high,xhigh}, so theGrokdefault resolves at every tier; a-fastvariant is an explicit id.- A model id is shell data. Accept only ids matching
^[A-Za-z0-9][A-Za-z0-9._:-]*$, block the issue otherwise, and single-quote the id in the shim.
3. The prompt file
Write the prompt to a file outside the repository tree (the session scratchpad, else mktemp -d). Append one line telling the CLI agent to read the work-on-issue skill (or fix-pr-review for a fix pass) at the first existing path of ~/.codex/skills/<skill>/SKILL.md, ~/.cursor/skills/<skill>/SKILL.md, ~/.claude/skills/<skill>/SKILL.md; resolve and write the absolute path yourself. Append the section 7 attribution rules.
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.
- 5d ago Changed · -8 lines 8a7312466fa4
- 6d ago Changed df0003e35d76
- 7d ago First seen · 91 lines · 101 tokens per session scan A 088cd23f0052
cli-dispatch is a skill published in the GitHub repository richkuo/rk-skills (49 stars, last pushed yesterday), licensed MIT. It adds 101 tokens to every session and 2,346 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
contradiction-analysis
A structured way to analyze difficult problems by identifying competing forces, finding the main conflict, and deciding which side or issue has the greatest effect.
mass-line
A method for collecting feedback and facts from multiple people or sources, turning them into a plan, and checking the plan with those affected.
practice-cognition
A method for testing ideas in practice, learning from the results, and improving the next attempt through repeated cycles.
protracted-strategy
A long-term planning method for difficult work that cannot be completed quickly, divided into stages with steady progress over time.
concentrate-forces
A decision-making method for situations where several tasks compete for limited time, attention, computing power, or budget.
workflows
A workflow guide for tasks that need several kinds of reasoning in sequence, such as research, finding the main conflict, choosing a small starting point, and planning sustained work.