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 pawbytes/skill-suites --skill paw-upwork-setupgit clone --depth 1 https://github.com/pawbytes/skill-suitesWrote 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/pawbytes/skill-suites/paw-upwork-setup)<a href="https://agentmods.dev/skills/pawbytes/skill-suites/paw-upwork-setup"><img src="https://agentmods.dev/badge/skills/pawbytes/skill-suites/paw-upwork-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/pawbytes/skill-suites/paw-upwork-setup"><img src="https://agentmods.dev/badge/skills/pawbytes/skill-suites/paw-upwork-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 | $0.00045 | $0.02205 |
| Opus 5.5 | $0.00018 | $0.00882 |
| Sonnet 5.5 | $0.00009 | $0.00441 |
| Haiku 4.5 | $0.00005 | $0.00220 |
Grade B, and why
paw-upwork-setup scanned grade B with 1 finding 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 1mo 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.
Subtle steeringmediumPrompt injection
Instructions that bias recommendations or shape behaviour without the user noticing.
Ask the user for values. Show defaults in brackets. Present all values together so the user can respond once with only what they want to change (e.g. "research mode manual, rest are fine"). Never tell the user to "press How it starts
The opening of the file, as written. The whole thing — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PawBytes Upwork Suite Setup
Overview
Installs and configures the PawBytes Upwork Suite into a project in a single guided pass: writes config, checks for (and offers to install) the browser-harness dependency that powers live market research, and scaffolds the per-freelancer workspace. Module identity (name, code, version) comes from assets/module.yaml.
Writes to:
{project-root}/.pawbytes/config/config.yaml— shared ecosystem config: core settings at root plus anupworksection. User-only keys (user_name,communication_language) are never written here.{project-root}/.pawbytes/config/config.user.yaml— gitignore-intended personal settings:user_name,communication_language, and any module variable markeduser_setting: true(default_freelancer,research_mode).{project-root}/.pawbytes/config/module-help.csv— registers module capabilities for the help system.
Both config scripts use an anti-zombie pattern — existing entries for this module are removed before writing fresh ones, so stale values never persist.
{project-root} is a literal token in config values — never substitute it with an actual path. It signals to the consuming LLM that the value is relative to the project root, not the skill root.
Identity
A setup specialist for the PawBytes Upwork Suite. Efficient and user-friendly during first-time installation and updates, and honest about the one real dependency (browser-harness) — installing it when wanted, falling back gracefully when not.
Principles
- Never hard-block. If browser-harness can't be installed, set
research_mode: manualand continue. The suite always works. - Sensible defaults. Every setting has a default; users override only what matters.
- Clear confirmation. Always show what will change before writing files.
- One-shot configuration. Collect all values in a single exchange, not piecemeal.
- ToS-safe framing. Research uses the freelancer's own browser/session, read-only and research-grade — never auto-submits proposals or scrapes aggressively.
What ships with it
10 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.
- assets/module-help.csv 1.0 KB
- assets/module.yaml 1.7 KB
- scripts/__pycache__/merge-config.cpython-311.pyc 18 KB
- scripts/__pycache__/merge-help-csv.cpython-311.pyc 9.7 KB
- scripts/merge-config.py 14 KB runs code
- scripts/merge-help-csv.py 6.5 KB runs code
- scripts/tests/__pycache__/test-merge-config.cpython-311-pytest-9.0.2.pyc 16 KB
- scripts/tests/__pycache__/test-merge-help-csv.cpython-311-pytest-9.0.2.pyc 29 KB
- scripts/tests/test-merge-config.py 5.2 KB runs code
- scripts/tests/test-merge-help-csv.py 6.0 KB runs code
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.
- 1mo ago First seen · 150 lines · 45 tokens per session scan B e51e097b1c59
paw-upwork-setup is a skill published in the GitHub repository pawbytes/skill-suites (114 stars, last pushed 16d ago), licensed MIT. It adds 45 tokens to every session and 2,205 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it B with 1 finding (subtle steering). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
story-readiness
Is a story implementation-ready? Checks clear acceptance criteria, open questions, ADR refs. READY/NEEDS WORK/BLOCKED/NOT ASSESSED.
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
projects
List all managed projects with status, branch, open PRs, and open issue counts — portfolio-level view.
handle-linkedin-connection-request-signal
Use this skill when someone sends a team member an inbound LinkedIn connection request. An inbound request is a deliberate, ACTIVE first-party intent signal — meaningfully stronger than a passive profile view — and it deserves different scoring rules. The skill resolves and enriches the requester, gates them through…