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 liyana31811/Codexless --skill codexless-browser-repairgit clone --depth 1 https://github.com/liyana31811/CodexlessWrote 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/liyana31811/codexless/codexless-browser-repair)<a href="https://agentmods.dev/skills/liyana31811/codexless/codexless-browser-repair"><img src="https://agentmods.dev/badge/skills/liyana31811/codexless/codexless-browser-repair.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Rogue Agent · line 89 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00070 | $0.01716 |
| Opus 5 | $0.00035 | $0.00858 |
| Sonnet 5 | $0.00014 | $0.00343 |
| Haiku 4.5 | $0.00007 | $0.00172 |
Grade A, and why
codexless-browser-repair 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 8d 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 — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Codexless Browser Repair
Use this Skill only for a current-machine Codexless Browser compatibility failure after upstream Codex / Chrome Skill / Browser runtime changed. The normal product path is automatic compatibility through the Codexless scanner, fingerprint, and known adapters. This Skill is the last-resort self-rescue path for an unknown Browser drift.
Core contract
- Keep the user in the Chat entry point. Chat diagnoses and coordinates; Codex is called only when an unknown code-level Browser drift genuinely needs a repair worker.
- Start model-free. A Codex version/build change by itself is not a repair reason.
- Do not turn this Skill into a permanent compatibility framework, updater, daemon, or authority layer.
- Do not modify upstream Codex bundles, Chrome extension files,
.codex/pluginscache, or private Browser service internals. - Never widen Codex trust, permission profile, roots, network authority, or approval policy to make a repair pass.
- Never use private
turnEnded, forged rollout JSONL, fake Codex turn completion, or another unproven private cleanup path to manufacture Browser handback/release. - Ordinary website failures, login problems, selector/page-layout bugs, and normal Browser operation are not this Skill.
1. Identify the target before touching it
Determine whether the task targets:
- the Codexless household/source checkout, where a formal source fix is appropriate; or
- an installed Codexless release, where only a temporary local Browser repair is allowed.
Do not guess an install root from memory. Resolve it from the actual Codexless launcher/doctor/runtime context available on the machine. Do not treat the upstream Codex/Chrome plugin directory as the Codexless repair target.
2. Run model-free compatibility evidence first
From a Codexless tree that contains the compatibility reporter, run it in a host-state context that can read the current user Codex config, Skills, and plugin cache:
npm run compatibility:report
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.
- 8d ago First seen · 136 lines · 70 tokens per session scan A 43b24574da21
codexless-browser-repair is a skill published in the GitHub repository liyana31811/Codexless (84 stars, last pushed 2d ago), licensed Apache-2.0. It adds 70 tokens to every session and 1,716 once invoked, about $0.0003 per session on Opus 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 2026-08-30.
Other skills, from other repositories
rel-ai-debugging
Use when repository behavior is reproducibly wrong and needs causal diagnosis or repair, including errors, broken tests, crashes, regressions, failed contracts, or incorrect runtime behavior. Do not use for general audits or final verification when no active defect is being diagnosed.
rel-ai-investigation
Use for read-only repository questions that need evidence, including architecture audits, feasibility studies, dependency or caller tracing, impact analysis, implementation-status checks, and proof of how something works. Do not use to implement fixes or for final completion or release verification of changes already…
diagnosing-bugs
Diagnose bugs with a reproducible red signal, minimized case, ranked hypotheses, and regression test.
web-debug-workflow
Use when Web Debug is explicitly requested or a local web bug needs browser-grounded evidence such as DOM, console, network, debugger, framework runtime, responsive geometry, replay, or fix verification. Do not use for exact unit, Go, or Vitest failures with no browser symptom; keep those on the native runner path.
browser-doctor
Read-only health check on browser-control setup. Verifies browser binary, Playwright MCP Bridge extension presence, token file mode/contents, AIWG MCP registration, provider config injection, and optional workspace allow-list. Outputs pass/fail per check with remediation commands.
instance-performance-triage
Answer "the instance is slow" or "my nightly job never ran" from ServiceNow's own telemetry — transaction logs, syslog, systrigger, progress workers, execution trackers — instead of ad-hoc scripts that add to the load.