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 adbertram/cli-tools --skill upwork-cligit clone --depth 1 https://github.com/adbertram/cli-toolsWrote 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/adbertram/cli-tools/upwork-cli)<a href="https://agentmods.dev/skills/adbertram/cli-tools/upwork-cli"><img src="https://agentmods.dev/badge/skills/adbertram/cli-tools/upwork-cli/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/adbertram/cli-tools/upwork-cli"><img src="https://agentmods.dev/badge/skills/adbertram/cli-tools/upwork-cli.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 | $0.00084 | $0.01266 |
| Opus 5.5 | $0.00034 | $0.00506 |
| Sonnet 5.5 | $0.00017 | $0.00253 |
| Haiku 4.5 | $0.00008 | $0.00127 |
Grade A, and why
upwork-cli 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 today.
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 — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.
<quick_start>
The upwork CLI follows this pattern:
upwork <command-group> <action> [arguments] [options]
| Task | Command |
|---|---|
| Authenticate (all creds) | upwork auth login |
| Authenticate OAuth API only | upwork auth login --credential-type oauth_authorization_code |
| Check auth | upwork auth status |
| Search jobs (GraphQL API) | upwork jobs list --filter "query:eq:python" --limit 20 |
| Filter jobs by skills, sort | upwork jobs list --filter "skills:eq:python|automation" --sort recency |
| Get one job posting | upwork jobs get <id-or-ciphertext> |
| List supported profile fields | upwork profile list --table |
| Read profile attributes | Disabled: upwork profile get returns a Cloudflare/non-headed automation error |
| Show one field definition | upwork profile get bio |
| Preview a profile update | upwork profile update --dry-run --set title="..." |
| Apply a profile update | Disabled: upwork profile update --yes ... returns a Cloudflare/non-headed automation error |
| </quick_start> |
<essential_principles>
MANDATORY: Verify the live command shape before executing ANY upwork command.
Consult usage.json when the repo or installed package ships it. If usage.json is absent, use upwork --help, the relevant subcommand --help, and README.md instead. Never guess at command syntax.
- The CLI uses the shared
cli_tools_shared.BrowserAutomationCDP/browser-harness backend with a persistent profile, stealth launch flags, andnavigator.webdrivermasking. - Do not tell agents to set
HEADLESS=false, launch local Chrome/CDP, or use Computer Use when Adam says not to use a headed browser or not to interrupt him. - Non-interrupting options are: reuse the authenticated saved browser profile, clear stale CLI cache and retry once, use an internal/API or authenticated in-page fetch path if the CLI already exposes one, connect only to an already-running approved CDP endpoint, or run the headed/CDP handoff on a remote/non-watched browser host.
- Real system Chrome over CDP is the known avoidance surface for managed Cloudflare challenges, but local real Chrome is a GUI action and requires explicit current approval.
- Never solve, click through, refresh around, or pay a service to solve a human-verification challenge. If the Cloudflare/Turnstile challenge persists on all allowed non-interrupting paths, report the blocker and the browser surface that needs approval.
</essential_principles>
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.
- today First seen · 79 lines · 84 tokens per session scan A 5477260c1d65
upwork-cli is a skill published in the GitHub repository adbertram/cli-tools (6 stars, last pushed today), licensed MIT. It adds 84 tokens to every session and 1,266 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 2026-11-07.
upwork-cli compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| upwork-cliadbertram/cli-tools | Skill | 6 | today | MIT | A | 84 | Claude Code, Codex |
| opencli-autofixjackwener/OpenCLI | Skill | 31k | yesterday | Apache-2.0 | A | 61 | Claude Code |
| surfnicobailon/surf-cli | Skill | 684 | yesterday | MIT | A | 53 | Claude Code, Codex |
| rdc-cliBANANASJIM/rdc-cli | Skill | 193 | 14d ago | MIT | A | 82 | Claude Code, Codex |
| pixiv-cli-ciFlanChanXwO/pixiv-cli | Skill | 132 | yesterday | MIT | A | 61 | Codex |
| acrawl-mcpMingye-Lu/AgenticCrawler | Skill | 15 | yesterday | MIT | A | 200 | Claude Code, Codex |
| debug-hubrexleimo/aios | Skill | 62 | yesterday | MIT | B | 66 | Claude Code, Codex |