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 tae2089/harness --skill codex-harness-setupgit clone --depth 1 https://github.com/tae2089/harnessWrote 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/tae2089/harness/codex-harness-setup)<a href="https://agentmods.dev/skills/tae2089/harness/codex-harness-setup"><img src="https://agentmods.dev/badge/skills/tae2089/harness/codex-harness-setup/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/tae2089/harness/codex-harness-setup"><img src="https://agentmods.dev/badge/skills/tae2089/harness/codex-harness-setup.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 | $0.00067 | $0.00731 |
| Opus 5.5 | $0.00027 | $0.00292 |
| Sonnet 5.5 | $0.00013 | $0.00146 |
| Haiku 4.5 | $0.00007 | $0.00073 |
Grade A, and why
codex-harness-setup 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 27d 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 — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Codex Harness Setup
Configure project preferences for codex-harness. Use the existing shared tracker contract rather than a separate harness publication backend.
Procedure
- Read existing AGENTS.md and, when present,
.scratch/.tracker. Reuse decisions already made in the conversation. Do not inspect credential values or infer a tracker from the Git remote. - Load
../codex-harness/references/project-policy.md. If the companion skill is unavailable, report that dependency before generating an incomplete harness. - For tracker setup, locate the installed
to-issues/references/tracker-config.md, also used byto-spec. Use its supported keys and publication-tool rules. If missing, report the dependency; do not invent a replacement configuration. - Preserve valid existing tracker settings unless the user requests a change. For a missing configuration, explain the shared local fallback or collect the user's explicit destination. Do not create tickets or publish documents during setup. Issue-free execution does not require a tracker.
- Reuse the existing explanation profile; otherwise ask for domains and familiarity with suggested beginner/ELI5, practitioner, and specialist options plus free text. Support mixed expertise.
- Prepare the concrete configuration and AGENTS.md changes, then apply them within the user's authorization and project safety rules. Write only
.scratch/.trackerwhen selected and the relevant AGENTS.md sections. Keep the shared configuration trackable. Preserve unrelated content and existing work. - Set model and effort preferences from the companion
codex-harness/references/schemas/models.mdduring harness generation, not in the tracker. An unavailable model requires an explicit replacement decision. - Do not generate a local execution-state engine or a state-management agent. The main Orchestrator records progress on the selected work record and resumes from that record plus actual artifacts. Preserve legacy project files without automatic cleanup.
- Report changed paths and any missing publication tools or dependencies. Setup success is not a claim that a remote issue or document was created.
What ships with it
3 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.
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.
- 27d ago First seen · 45 lines · 67 tokens per session scan A 326f6512e939
codex-harness-setup is a skill published in the GitHub repository tae2089/harness (4 stars, last pushed 27d ago), licensed Apache-2.0. It adds 67 tokens to every session and 731 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 2026-09-20.
Other skills, from other repositories
md-hive-sync
Munder Difflin hive sync — runs the start-of-task hive protocol steps: reads memory.md, checks inbox/ for new messages, and reminds you to record durable facts in memory.md and write coordination files before ending. Use when asked to "sync with the hive", "check my inbox", "hive status", or "hive sync". Proactively…
standup-update
Generate a concise standup update from the user's recent work GitHub activity, including the previous work period and today. Use when the user asks what they worked on, requests a standup update, or invokes /standup.
task-final-report
Apply the final report and PR publication procedure for a Hyper-Waterfall task. Write the final report (report.md), mark the daily task board complete, create the final commit, push the remote publish/task{N} branch, and create an Open PR to {BASEBRANCH}. Invoke only immediately before PR publication after all stages…
task-register
Register a new task that does not yet have a GitHub Issue in the Hyper-Waterfall workflow. Query open milestones and existing labels, choose candidates, confirm with the task requester before creating the Issue, then create the GitHub Issue number. After Issue creation, hand off branch, daily task board, and task plan…
todo
Create and update the Hyper-Waterfall daily task board (mydocs/orders/yyyymmdd.md). Apply milestone table format, status update rules, and backlog section rules. When task-start, task-stage-report, task-final-report, or pr-merge-cleanup updates the daily task board, it follows this SKILL's format.
task-stage-report
Apply the stage completion procedure for a Hyper-Waterfall task. Write the stage report (stage{N}.md), commit stage source and report together, and run stage verification commands. Invoke after a stage completes and before entering the next stage.