Borrowing it
Nothing to install: this file belongs to Eduardo-Salvador/Agent-Harness-Kit. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Eduardo-Salvador/Agent-Harness-Kit/main/.agents/skills/codex-agent-dispatch/SKILL.mdgit clone --depth 1 https://github.com/Eduardo-Salvador/Agent-Harness-KitWrote 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/eduardo-salvador/agent-harness-kit/codex-agent-dispatch)<a href="https://agentmods.dev/skills/eduardo-salvador/agent-harness-kit/codex-agent-dispatch"><img src="https://agentmods.dev/badge/skills/eduardo-salvador/agent-harness-kit/codex-agent-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/eduardo-salvador/agent-harness-kit/codex-agent-dispatch"><img src="https://agentmods.dev/badge/skills/eduardo-salvador/agent-harness-kit/codex-agent-dispatch.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00056 | $0.00432 |
| Opus 5.5 | $0.00022 | $0.00173 |
| Sonnet 5.5 | $0.00011 | $0.00086 |
| Haiku 4.5 | $0.00006 | $0.00043 |
Grade A, and why
codex-agent-dispatch 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 2mo 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
Codex agent dispatch
Follow ../../../docs/contracts/CODEX-AGENT-DISPATCH.md and ../../../adapters/codex.md. This is the executable Codex bridge from neutral role/task artifacts to a live agent context.
- Build a request from the pinned
TASK.md, resolvedharness.model-dispatch/v1, and current capability evidence. Include only the role, task SPEC, approved authority/rule references,read_set, andimpact_set; never include the conversation, full plan, or broad repository context. - Run
agent-harness codex-dispatch <request.json>and inspect the machine-readable plan. For implementation, retain the requested specialist identity and userole:generic-specialistwhen no dedicated neutral executor exists. For review, forcerole:reviewer-integrator, a distinct identity, andfork_turns: none. - When status is
ready-to-dispatch, invoke the named native operation using exactlynative_call.arguments, including model and reasoning effort. Do not claim dispatch before the host returns an agent/context reference. - Persist the sanitized host response, then run
agent-harness codex-dispatch <plan.json> --response <response.json>. Link the resultingharness.codex-agent-dispatch/v1record from the task/graph transition before marking the child active. - An implementation request with no subagent capability records
sequential-fallbackand runs visibly in the orchestrator context. A review request recordsmanual-fresh-context-required; same-context review is forbidden even under fallback. - Implementer and reviewer identities, contexts, packets, and dispatch evidence remain distinct. A user-visible Codex task is created only when the user explicitly requests one; the normal route is an internal subagent.
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.
- 2mo ago First seen · 16 lines · 56 tokens per session scan A 8747a236f0f1
codex-agent-dispatch is a skill published in the GitHub repository Eduardo-Salvador/Agent-Harness-Kit (6 stars, last pushed 1mo ago), licensed MIT. It adds 56 tokens to every session and 432 once invoked, about $0.0002 per session on Opus 5.5. 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
forming-an-openrig-mental-model
Use when the system around you does not make sense yet: you just booted into a seat and do not know how the pieces fit; someone said rig, pod, seat, fleet, topology, or slice and you are not certain what they mean here; you are unsure what kind of rig you are in or what it is for; you do not know how skills reach you…
orienting-to-an-inherited-seat
Use when you have just been primed into an EXISTING seat through a planned handover — a different agent retired and handed you the seat plus its earned context — and you need a world model of what just happened to you. Covers how a handover differs from compaction and from a fresh launch, the…
agent-browser
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a…
applying-a-permission-policy
Use before launching a team during agent-guided setup, or when a user asks to configure OpenRig command permissions, reduce repeated native approval prompts, or apply a selected rig/seat permission policy.
messaging-the-human
Use when project policy calls for a human decision or update, a human delivery is pending or failed, or a reply must resume the right work.
openrig-upgrade
Use when an agent is preparing or performing an OpenRig CLI/daemon upgrade and must preserve live seats, verify each mutation, or reconcile managed plugin and skill files without overwriting local work.