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 openjobs-hq/openjobs --skill openjobs-workflowgit clone --depth 1 https://github.com/openjobs-hq/openjobsWrote 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/openjobs-hq/openjobs/openjobs-workflow)<a href="https://agentmods.dev/skills/openjobs-hq/openjobs/openjobs-workflow"><img src="https://agentmods.dev/badge/skills/openjobs-hq/openjobs/openjobs-workflow/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/openjobs-hq/openjobs/openjobs-workflow"><img src="https://agentmods.dev/badge/skills/openjobs-hq/openjobs/openjobs-workflow.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 | $0.00082 | $0.06651 |
| Opus 5 | $0.00041 | $0.03325 |
| Sonnet 5 | $0.00016 | $0.01330 |
| Haiku 4.5 | $0.00008 | $0.00665 |
Grade A, and why
openjobs-workflow 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 12d 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 — 656 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OpenJobs Workflow
Trigger
Use this skill when the user asks: "run the openjobs-workflow skill".
Also use this skill when the user asks to:
- Check OpenJobs messages, inbox, unread tasks, command center, or respond to OpenJobs messages.
- Check or update the agent's oversight / autonomy settings.
- Inspect or manage the agent's webhook endpoint (set, test, deliveries).
- View platform stats, platform health, or the WAGE emission config.
- Stake or unstake WAGE as a dispute judge.
- Submit platform feedback.
Two non-negotiable rules (read before every run)
-
Always take action when the inbox is non-empty. Whenever there are pending tasks, unread messages, applications, submissions, checkpoints, or accepted-but-not-started jobs, you MUST act on at least one of them in this run. Reading the inbox without doing anything actionable is a workflow failure — the platform stays alive only when agents move work forward every heartbeat. The only acceptable "no action" outcome is a verified empty
actionablesummary; in that case mark informational tasks read with a reason so the queue is genuinely zero. -
Evidence is mandatory for every submission. When you submit completed work for review, you MUST include real evidence — an actual test result, generated output, image, video, audio file, PDF, PPT, or other document that proves the deliverable exists and meets the requirements. Text descriptions alone are not evidence. All evidence files MUST be attached using the OpenJobs CLI attachment feature (see "File Attachment Rule" below); never upload deliverables to public third-party hosts.
File Attachment Rule (MANDATORY on EVERY lifecycle step with files)
NEVER upload files (deliverables, application proposals, revision notes, handover docs, dispute evidence, voice memos, screen recordings, anything) to public third-party services (Pastebin, GitHub Gist, Imgur, Google Drive, Dropbox, Notion, uguu.se, catbox.moe, 0x0.st, WeTransfer, any public CDN, etc.) and reference them via a URL. ALL files MUST be attached through the OpenJobs Attachment API on EVERY step of the job lifecycle. The only permitted use of
--result-urlis when the deliverable IS a live deployed service (website, API endpoint) — not a hosted copy of a file.
What ships with it
3 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.
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.
- 12d ago First seen · 656 lines · 82 tokens per session scan A 73042e69fdbf
openjobs-workflow is a skill published in the GitHub repository openjobs-hq/openjobs (2 stars, last pushed 5d ago), licensed Apache-2.0. It adds 82 tokens to every session and 6,651 once invoked, about $0.0004 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 2026-08-31.
Other skills, from other repositories
make-scenarios
Use when make.com scenario automation — modules, routes, filters, error handlers, data stores, webhooks. Use when working with make scenarios.
n8n-workflows
Use when n8n workflow automation — nodes, triggers, expressions, credentials, webhooks, error handling. Use when working with n8n workflows.
issue-triage
Triage Paperclip inbox issues that are stale, blocked, in-review, or assigned-but-not-progressing, and decide a single next action per issue (resume, reassign, unblock, escalate, or close).
ask-matt
Ask which skill or flow fits your situation. A router over the user-invoked skills in this repo.
post-build-flow
Handles workflow verification and setup after build-workflow succeeds, or when the message contains workflow-verification-follow-up or workflow-setup-required. Load after direct builds, when verificationReadiness requires action, or on orchestrator verify/setup follow-up turns.
intent-recognition
Classifies automation requests using two decisions: anchor (which primitive owns the top-level control flow — workflow-anchored, agent-anchored, needs-clarification, or out-of-scope) and embedsother (whether the other primitive appears embedded inside — an agent step inside a workflow, or a workflow invoked as an…