Turn Codex into your coding orchestrator
Dramatically improve your Codex usage with this skill.
Sol Foreman is a free, open-source skill for Codex. Your main agent stops being the one typing and becomes the one running the job — it decides what done looks like before it hires anyone, hands bounded tickets to the right worker, and refuses to accept a single one until an independent verifier, who never saw how the work was built, reproduces the proof.
Version 0.2.0 · Released July 19, 2026 · MIT licensed
Get the install line →Codex is very good at doing the work. It is not good at knowing whether the work is finished.
That gap is where your usage goes to die. An agent that types for an hour and then reports done has told you exactly one thing: that it stopped. Whether the tests actually pass, whether it wandered into files you never authorized, whether the fix survives the edge case that started all this — none of that is in the word done.
Sol Foreman puts a boss over that. Your Codex session becomes a job site: proof defined up front, work handed out in bounded tickets, and a verifier who assumes the job is broken until it can show otherwise.
Get Sol Foreman
Free and MIT licensed. The repo is the home of the skill — grab it on GitHub, read the sixteen small files, and install it. You need Codex with global skill support and Python 3.9 or newer.
Step 1 — Install it
Copy this and paste it into Codex. That's the whole install — Codex's own skill installer pulls the pinned v0.2.0 release and puts it where it belongs. Works the same on Mac, Windows, and Linux.
Use $skill-installer to install https://github.com/olsenbrands/sol-foreman/tree/v0.2.0/skills/sol-foreman globally.Start a fresh Codex session afterward so the skill catalog picks it up. You're done when typing $sol-foreman offers the skill.
Prefer to run the installer command yourself? ▾
macOS / Linux
python3 "${CODEX_HOME:-$HOME/.codex}/skills/.system/skill-installer/scripts/install-skill-from-github.py" \
--repo olsenbrands/sol-foreman \
--path skills/sol-foreman \
--ref v0.2.0Windows
py "%USERPROFILE%\.codex\skills\.system\skill-installer\scripts\install-skill-from-github.py" --repo olsenbrands/sol-foreman --path skills/sol-foreman --ref v0.2.0Step 2 — Put it to work
Paste one of these above your actual request. Use the first for a single bounded job, the second when you're handing Codex a whole tracker or plan to run.
Use $sol-foreman to delegate this task to one suitable worker, define the verification criteria first, and independently verify the result.Use $sol-foreman to understand this repository and tracker, define what done means, select a bounded pilot, route the right agents, monitor and verify their work, and continue only while accepted throughput supports the plan.You're done when Codex writes out what “done” looks like and names the crew it's about to hire — before it spends a cent on workers.
You've felt both of these
If you've run Codex on anything real, you know the two failure modes by heart:
“You hand Codex a big job, it works for an hour, says “done” — and you find out three files later that it never was.”
“You let it fan out across a plan and watched your usage drain into work nobody checked.”
The problem was never Codex. It was that nobody gave it a definition of finished it had to earn.
What it actually does
Sol Foreman is instructions, not an app — a skill your Codex reads and follows, plus seven small Python scripts that do the checking it can't be trusted to do in its own head. No daemons, no accounts, no telemetry. Here's the system it installs:
- 1.
It decides what “done” means before it hires anyone.
Sol Foreman writes down the observable proof first — the exact test, gate, or thing you can look at — derived from your goal, not from the ticket. Only then does it pick a worker. A job that can't be described as proof doesn't get dispatched; it gets a read-only scouting run instead.
- 2.
It routes by leftover judgment, not by task size.
Once a ticket is fully specified, the question is how much judgment is still left in it. A sprawling mechanical rename has almost none — that's fast, cheap-seat work. A ten-line concurrency fix is packed with it — that's flagship work. Each ticket then goes to the least costly seat that clearly clears the bar.
“Choose economics only among seats that clearly meet the quality floor. Route upward when uncertain.”— the First Law, verbatim from the skill
- 3.
It hires from three crews — and yours might only have one.
Native Codex subagents, Codex CLI workers pinned to an exact model, and Claude CLI workers for cross-family review. Sol Foreman runs a local, non-billable check to see which of those your machine actually has. Missing a crew doesn't get faked — it degrades honestly and tells you what it lost.
- 4.
It runs a pilot before it spends real money.
On anything long — more than ten tracked items, over an hour of forecast, or a migration, auth, payments, or concurrency seam — it's only allowed one or two pilot tickets. Broader dispatch stays locked until a pilot genuinely finishes a real item and you approve the projection. No launching a twelve-agent wave just because the dependency graph allows it.
- 5.
It trusts no one — including itself.
Every meaningful change goes to a fresh verifier with read-only tools, handed your original request and an isolated product-only copy — never the builder's retelling. Builders can't certify their own work, and the code is fingerprinted before and after so nobody can quietly edit what they're judging. When you have both CLIs, Claude can verify Codex's work and vice versa.
- 6.
It knows when to stop.
Two failures from the same root cause halt new fan-out until there's a substantive new plan. A third attempt has to change the worker and the route, not just try again harder. Work that's been reported but not yet verified still counts against capacity, so a backlog of unchecked “done” can't hide behind a green progress bar.
Two modes, so small jobs stay small
All of that discipline would be exhausting on a one-file fix, so it doesn't apply there. Sol Foreman picks its own weight class:
Lightweight
When: One bounded, low-risk job under about thirty minutes.
What you get: Inline criteria, one worker, one write set, lead verification. No ledger, no JSON, no ceremony.
Program
When: Multiple tickets, parallel writes, long jobs, or a risky seam like a migration or auth change.
What you get: Machine-checked tickets, append-only state, a mandatory pilot, circuit breakers, and exact progress counted in original items — not worker activity.
And if a light job grows past its boundary mid-run, it gets promoted to the heavier mode before anything else is dispatched.
About your usage — the honest version
This is about smarter spend, not a discount. Sol Foreman won't promise a percentage off your bill, and it will happily spend more on a job that needs it — the rule is written the other way around on purpose: economics only gets to choose among the seats that already clear the quality bar, and when quality is uncertain it routes upward, not down.
What it does stop is the expensive kind of waste — your flagship seat doing find-and-replace, an unchecked “done” that costs you a second run tomorrow, and a wave of agents grinding through the same broken assumption. Two failures with the same root cause and new work stops until there's a real plan. It reports what was actually accepted and what it projects from there, rather than hiding behind a big cached-token total.
Built in public — and stress-tested until it stopped breaking
The skill ships with 65 dependency-free tests — including a complete 45-item program run — covering ticket preflight, retry and breaker behavior, candidate isolation, cross-platform path safety, process closure, and privacy-safe capability probing. You can run the whole suite yourself from a fresh checkout in a few seconds.
Before release it was handed to fresh leads that had never seen the answer key, on scenarios rigged to fool them — a worker reporting DONE on work that hadn't passed, an unauthorized file edit buried in a good-looking diff, prose criteria too vague to verify. Then three independent Opus 4.8 reviews went at it read-only, and a final Codex reviewer reproduced a real crash and failed the release — it only passed after the fix and a regression test that pins it.
So the skill that teaches Codex to distrust AI self-reports was itself failed by an AI reviewer before it shipped. That's a stress test, not an endorsement — and the commit history on GitHub shows every round.
Who it's for
- →Codex users who've been burned by a confident “done” that wasn't.
- →Anyone handing Codex a whole tracker or plan instead of one file at a time.
- →People running both Codex and Claude who want one checking the other's work.
- →Anyone who wants their flagship seat spent on decisions instead of typing.
It's sixteen files. Read them yourself.
No daemons, no telemetry, no magic. Sol Foreman is one SKILL.md, six reference docs, seven dependency-free Python scripts, an agent manifest, and its license. Clone it and run python3 -m unittest discover -s tests to watch all 65 tests pass on your own machine — which is rather the point of a skill built on verifying instead of trusting.
Frequently asked questions
What is Sol Foreman?
A free, open-source skill for Codex. It makes your main Codex agent act as a foreman — it works out what finished actually looks like, hands bounded tickets to the right worker, watches the job, and personally accepts or rejects the result. A worker saying it's done is treated as a claim, not proof.
Is it really free?
Yes. MIT licensed, version 0.2.0, released July 19, 2026. It's sixteen files — one instruction file, six reference docs, seven small Python scripts, an agent manifest, and its license. No daemons, no accounts, no telemetry.
What do I need to run it?
Codex with global skill support and Python 3.9 or newer for the helper scripts. That's the floor. The Codex CLI and the Claude Code CLI are both optional — they unlock model-pinned workers, but the skill runs without either and tells you plainly what it can't do.
Do I need a Claude subscription too?
No. If you have the Claude CLI installed, Sol Foreman can hire Claude workers alongside Codex ones — useful when you want a different model family checking Codex's homework. No Claude? Everything routes to Codex lanes and nothing breaks. Claude Fable 5 in particular is never used without asking you first, because it draws on a separate expensive quota.
Will this cut my Codex usage?
It's about smarter spend, not a discount. Sol Foreman keeps your flagship seat on the judgment calls and hands mechanical work to cheaper, faster seats — but the rule is explicit that economics only chooses among models that clearly clear the quality bar, and it routes upward when quality is uncertain. It also refuses to burn budget on a runaway loop: two failures from the same root cause stop new work until there's a real new plan.
How do I know the work actually got checked?
Every meaningful change goes to a fresh verifier that never saw how the work was built. It gets your original request, the exact criteria, and an isolated copy of the product — not the builder's story about it. Builders are never allowed to certify their own work, and the skill fingerprints the code before and after so a verifier can't quietly edit what it's supposed to be judging.
Has it been tested, or is this vibe-coded?
It ships with 65 dependency-free tests, including a full 45-item program trace. Before release it went through three independent read-only Opus 4.8 reviews and a Codex review that reproduced a real crash, failed the release, and only passed after the fix and a regression test. The commit history on GitHub shows every round.
Put Codex in charge of the job
Grab Sol Foreman on GitHub — free, MIT licensed, and one paste to install.
Get the install line →Don't sleep on what's next
Get the next tool before everyone else
Free tools, prompts, and skills for Codex, Claude Code, and OpenClaw — sent when they drop. No spam, unsubscribe anytime.
The Claude Code version
Fable Foreman
Same idea, other side of the fence: a free Claude Code skill that makes your strongest Claude model plan and verify while cheaper workers do the typing.
Keep exploring
More free AI tools and guides from Don't Sleep On AI
NEW — v3.4.1Did We Drift
A free Claude Code skill that reads your plan, reads your commits, and says straight whether your agent drifted.
NEWThe Fable 5 Holy Grail of Skills
Three installs that turn Fable 5 into an orchestrator: Fable Foreman to plan and verify, the Codex CLI to do the typing, and the Fable Safe Prompt to keep you on Fable.
Prompt Fable 5 Without Security Triggers
A free prompt that turns Opus 4.8 into a Fable-safe prompt writer, so security and biology classifiers stop misreading legitimate work.
An agent that says “done” has only told you it stopped. Make it prove the rest.
Don't sleep on AI.
