What is codex-harness?

A planning tool for the Codex command-line environment that designs teams of specialized helper agents, their instructions, and the project files they need.

Use it to set up a Codex agent team, create agent definition files and skills, and initialize project instructions for domain-specific automation.

It removes the need to design agent roles, permissions, workflows, and shared project guidance from scratch.

codex-harness — Skill for Claude Code and Codex by tae2089/harness

Install

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.

Any agent

npx skills add tae2089/harness --skill codex-harness

Clone the repo

git clone --depth 1 https://github.com/tae2089/harness

Made for: Claude Code, Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/tae2089/harness/codex-harness/github.svg)](https://agentmods.dev/skills/tae2089/harness/codex-harness)

Your own site

<a href="https://agentmods.dev/skills/tae2089/harness/codex-harness"><img src="https://agentmods.dev/badge/skills/tae2089/harness/codex-harness/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/tae2089/harness/codex-harness"><img src="https://agentmods.dev/badge/skills/tae2089/harness/codex-harness.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 74 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,520 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00074	$0.01520
Opus 5.5	$0.00030	$0.00608
Sonnet 5.5	$0.00015	$0.00304
Haiku 4.5	$0.00007	$0.00152

Measured 29d ago against content hash 0c3d6474fe5c, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

codex-harness 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 29d 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.

skills/codex-harness/SKILL.md · 116 lines

How it starts

The opening of the file, as written. The whole thing — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Codex Harness Meta-Skill

Generate a project-specific harness using native Codex subagents, shared work records, and verifiable outputs. The main Orchestrator delegates and aggregates; no separate agent-team runtime or local execution-state engine is required.

Phase 0: Inspect and scope

Read existing project instructions, agent definitions, skills, and the current request. Preserve user edits and decisions already supplied. Do not treat the presence of an old execution workspace as a reason to resume or reset it.

For an existing harness, use references/expansion-matrix.md. For request examples, use references/usage-examples.md. Only generate or modify the components needed for the request.

Phase 1: Work and audience policy

Apply references/project-policy.md:

Natural-language requests are valid inputs. For actionable work, ask existing issue / new issue / no issue only if the user has not already chosen.
Share .scratch/.tracker with to-spec and to-issues; do not introduce another tracker configuration.
One issue represents a work unit with completion criteria, not an agent invocation or retry.
Read the selected issue/spec and actual project artifacts before executing or resuming work.
Update progress and evidence at meaningful milestones. Close an issue only on user request.
Reuse the existing explanation profile, or ask for domain-specific familiarity with suggested choices and free text before writing AGENTS.md.

The publication skills and their shared tracker contract are external dependencies. Missing dependencies must be reported; they do not prevent explicitly issue-free work.

Phase 2: Roles and coordination

Choose the smallest sufficient set of roles from references/schemas/models.md. Do not generate a State Manager. Single focused work may run directly; delegate only when the work benefits from a separate role.

Use references/agent-design-patterns.md to choose sequential, parallel, review-loop, specialist, supervisor, hierarchical, or handoff coordination. Only the main Orchestrator spawns subagents. Team leads propose decomposition; they do not spawn workers.

Read the full file on GitHub · 116 lines

Files

What ships with it

28 files 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.

Changes

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.

29d ago Changed · -94 lines · -27 tokens per session 0c3d6474fe5c
1mo ago First seen · 210 lines · 101 tokens per session scan A a22207d6b3a7

Subscribe to this mod's changes

codex-harness is a skill published in the GitHub repository tae2089/harness (4 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 74 tokens to every session and 1,520 once invoked, about $0.0003 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.

Building agents Planning agents-skills ai coding-agent gemini-cli harness harness-engineering

last30Days

Resolve "last30Days" to a concrete ISO date range relative to your run time — a rolling 30-day window ending today. Returns inclusive civil dates plus exact UTC instants so you have temporal context without computing dates by hand. Read-only: no writes, no network. Use before a "last 30 days" / trailing-month task…

chaitanyagiri/munder-difflin · 83 tokens

thisQuarter

Resolve "thisQuarter" to a concrete ISO date range relative to your run time — this quarter so far (quarter start → today). Returns inclusive civil dates plus exact UTC instants so you have temporal context without computing dates by hand. Read-only: no writes, no network. Use before a quarter-to-date task (QTD…

chaitanyagiri/munder-difflin · 78 tokens

thisWeek

Resolve "thisWeek" to a concrete ISO date range relative to your run time — this week so far (Monday → today). Returns inclusive civil dates plus exact UTC instants so you have temporal context without computing dates by hand. Read-only: no writes, no network. Use before a week-to-date task (this week's activity…

chaitanyagiri/munder-difflin · 77 tokens

harness

A meta-skill for designing and maintaining a project harness: a coordinated set of specialist agents, skills, and project instructions. It defines their roles, connects them to the project, and updates the setup as the work changes.

revfactory/harness · 184 tokens

evolve

A workflow for improving an existing setup that guides coding agents. It collects results and feedback, compares the current setup with its starting version, and records useful changes.