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 fallow-rs/fallow-skills --skill fallow-codex-onboardinggit clone --depth 1 https://github.com/fallow-rs/fallow-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/fallow-rs/fallow-skills/fallow-codex-onboarding)<a href="https://agentmods.dev/skills/fallow-rs/fallow-skills/fallow-codex-onboarding"><img src="https://agentmods.dev/badge/skills/fallow-rs/fallow-skills/fallow-codex-onboarding/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/fallow-rs/fallow-skills/fallow-codex-onboarding"><img src="https://agentmods.dev/badge/skills/fallow-rs/fallow-skills/fallow-codex-onboarding.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 | $0.00109 | $0.00740 |
| Opus 5.5 | $0.00044 | $0.00296 |
| Sonnet 5.5 | $0.00022 | $0.00148 |
| Haiku 4.5 | $0.00011 | $0.00074 |
Grade A, and why
fallow-codex-onboarding 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 7d 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Set up Fallow in Codex
Use the Fallow app tools. Keep each step short. Ask one question at a time.
1. Check the installation
Call fallow_check_install with {}.
- If it reports a version, continue.
- If fallow is missing, explain that the app runs the fallow CLI locally and
that no code leaves the machine. Offer to install it globally with
npm install --global fallow. The sidebar dashboard needs a fallow on PATH, because the app runs a copy inside the project only within the Codex sandbox of a thread. Run the install only after the user agrees. Then callfallow_check_installagain.
2. Choose the defaults
Call fallow_settings_read with {}. Ask these questions, one at a time.
Skip a question when the user already answered it.
- "Analyze the whole project by default, or only the files your branch
changed?" Map the whole project to
scope: "full"and changed files toscope: "changed". - "Leave tests, stories and dev tooling out of the analysis?" Map yes to
production: true.
Call fallow_settings_update with a set object that holds only the changed
values, for example {"set":{"scope":"changed"}}. Skip the call when nothing
changed. Report the saved values from the tool result. Do not say that a value
was saved when the call failed.
3. Run the first analysis
Call fallow_analyze with {}. The user sees the dashboard. In two or three
sentences, give the health score, the largest category of findings, and one
finding to start with.
If the result says that no project is known, ask the user to open a project
folder in this thread, then call fallow_analyze again.
4. Show what the app adds
Tell the user, in a short list:
- Fallow in the sidebar opens the full dashboard.
- Code Health opens beside a thread and follows the project of that thread.
- Type @Fallow in the composer to attach a finding or all findings of a rule.
- Open
.fallowrc.jsonor.fallowrc.jsoncto edit rules and preview their impact before saving..sariffiles open in a findings viewer. - Before a commit, ask Codex to audit the branch.
What ships with it
1 file 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.
- 7d ago First seen · 71 lines · 109 tokens per session scan A 844f5bb9edce
fallow-codex-onboarding is a skill published in the GitHub repository fallow-rs/fallow-skills (131 stars, last pushed today), licensed MIT. It adds 109 tokens to every session and 740 once invoked, about $0.0004 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 2026-10-10.
Other skills, from other repositories
cmux-test-bisect
Find when and why tests broke on main: bisect a Swift package suite on CI across old commits, read the failure matrix, and decide per test whether the test went stale or the code regressed. Use when a suite is red on main, when PR CI only ran filtered tests and the full suite has drifted, or when asked which PR broke…
cmux-debugging
Debug logging, Debug menu, runtime pitfalls, typing-latency-sensitive paths, SwiftUI list snapshot boundaries, OS-version repros, and local visual iteration for cmux. Use when adding debug probes, diagnosing UI/runtime issues, touching terminal rendering, tab/sidebar list views, drag/drop UTTypes, or using the Debug…
cmux-diagnostics
Run end-user cmux diagnostics. Use when cmux hooks, notifications, session restore, settings, browser automation, socket access, CLI control, or agent resume behavior is not working, or when the user asks for a cmux health check, doctor report, or support-safe debug summary.
cmux-capture
Screenshot or record a cmux window from the CLI, for a pull request, a bug report, or to see what the app actually looks like right now. Use when a change is visual, when a drag or an animation cannot be described in text, or when a reviewer needs evidence rather than a claim.
retro
Review a coding session and propose environment changes that prevent repeated agent mistakes.
diagnosing-bugs
Build a tight, red-capable feedback loop before diagnosing failures, then minimize, test ranked hypotheses, and lock the fix with a regression test.