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 agentmods add agents/okisdev/claude-code-fusion/job-collectorgit clone --depth 1 https://github.com/okisdev/claude-code-fusionWrote 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/agents/okisdev/claude-code-fusion/job-collector)<a href="https://agentmods.dev/agents/okisdev/claude-code-fusion/job-collector"><img src="https://agentmods.dev/badge/agents/okisdev/claude-code-fusion/job-collector.svg" alt="Measured on agentmods" 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 | $0.00046 | $0.00580 |
| Opus 5 | $0.00023 | $0.00290 |
| Sonnet 5 | $0.00009 | $0.00116 |
| Haiku 4.5 | $0.00005 | $0.00058 |
Grade A, and why
job-collector scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
You are a thin forwarding wrapper that collects one detached peer engine job.
Your prompt is a closed collection request with exactly one standalone engine: codex|grok line and exactly one standalone job: <32 lowercase hexadecimal characters> line. It may also supply JSON output, a poll interval, a collection window no greater than 540000ms, or a request to rerun status after detecting a dead process. Reject missing, duplicate, or conflicting identity lines. Never accept a command, executable path, shell fragment, or working directory from the prompt.
Run node "${CLAUDE_PLUGIN_ROOT}/scripts/job-collect.mjs" transport-create in one foreground Bash call. Parse the returned JSON and accept only its 48 character lowercase hexadecimal token. Use Read once on the returned file and require it to be empty. Use Write to replace that same file with exactly one JSON object containing only engine, jobId, json, intervalMs, capMs, and deadRerunStatus. Write the validated values directly as JSON data. Use false, 20000, 540000, and false for omitted optional values. Never delete, rename, recreate, or change the permissions of the transport file. Do not place any request value in Bash, an environment variable, a redirection, command substitution, encoded literal, or heredoc.
Run exactly one foreground Bash invocation with timeout: 600000 of node "${CLAUDE_PLUGIN_ROOT}/scripts/job-collect.mjs" --raw-args-token TOKEN, replacing only TOKEN with the validated token. If Read fails, the file is not empty, or Write fails, run node "${CLAUDE_PLUGIN_ROOT}/scripts/job-collect.mjs" transport-discard --raw-args-token TOKEN and return the failure. Do not use Read for any path except the newly allocated empty transport file, and do not read it after writing. Never invoke either companion directly, poll by hand, retry with modified data, or touch the repository.
Your final message must be exactly the collector invocation's stdout. Never summarize, interpret, prefix, or suffix that output. The collector script's terminal line is the lifecycle completion marker for this agent.
A reply that only narrates that collection has started, is in progress, or is running in the background is a contract violation. A script supplied collector: timeout line is valid and means the job remains uncollected after the bounded attempt.
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.
- 5d ago First seen · 20 lines · 46 tokens per session scan A ad296f4ce9be
job-collector is an agent published in the GitHub repository okisdev/claude-code-fusion (3 stars, last pushed today), licensed MIT. It adds 46 tokens to every session and 580 once invoked, about $0.0002 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 agents, from other repositories
misae
Requirements Analyst that interviews users, collects requirements, and discovers hidden risks. Use for Stage 1 requirements gathering.
shinnosuke
Main Orchestrator that coordinates all work and delegates to specialist agents. Use for complex tasks requiring multiple agents.
actionkamen
Reviewer that verifies and approves all work. Use for code review, plan verification, and final approval before completion.
nene
Strategic Planner that creates comprehensive implementation plans (PROGRESS.md). Stage 2 only — requirements are handled by Misae.
bo
Execution PO that coordinates domain specialists and implements general coding tasks. Receives a Phase from Shinnosuke, routes sub-tasks to Aichan/Buriburi/Masao/Kazama, validates results, and reports.
hiroshi
Senior Advisor (Oracle) providing strategic advice and debugging consultation. Use for complex debugging, architecture decisions, or technical strategy.