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 skills/wayne930242/straw-boss/dispatching-worknpx skills add wayne930242/straw-boss --skill dispatching-workgit clone --depth 1 https://github.com/wayne930242/straw-bossWrote 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/wayne930242/straw-boss/dispatching-work)<a href="https://agentmods.dev/skills/wayne930242/straw-boss/dispatching-work"><img src="https://agentmods.dev/badge/skills/wayne930242/straw-boss/dispatching-work.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 | $0.00150 | $0.04780 |
| Opus 5 | $0.00075 | $0.02390 |
| Sonnet 5 | $0.00030 | $0.00956 |
| Haiku 4.5 | $0.00015 | $0.00478 |
Grade A, and why
dispatching-work 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 3d 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 — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Overview
See docs/roles.md for the smallest sufficient loop boundary. This skill implements dispatch mechanics once a separate workroom is selected; a launched Herdr agent and the user choose its specification, design, implementation, and the verification method inside the reality anchor the brief names.
The unit this skill manages is the agent, not the app. An app (.claude/straw-boss/apps.json, resolved upstream by work-on) is only where an agent is rooted — this skill starts the agent there, tracks it, and closes it out; it never itself decides which app a request belongs to. Every dispatched task is one agent, tracked as one instruction file under ~/.straw-boss/dispatch/ — the user's home directory, not the target project checkout (see init). This skill covers: dispatch a single agent (Tasks 1-5), dispatch a plan (Branch below, when work-on produced a multi-task dependency graph — one agent per task), list, and wrap up. Exact CLI/JSON syntax lives in references/ — dispatch-mechanics.md (single-agent dispatch + permission-mode detection), plan-mechanics.md (plan/status schemas, worktree repair heredoc, and the provider-neutral status watcher), cross-session-coordination.md (making the main agent addressable — herdr pane id primary, with provider-specific fast channels — plus mid-task interrupt syntax), shared-resource-coordination.md (a worktree isolates files, not a fixed port or a shared DB another main agent's task might collide on — one command per case: claim-port for a flexible port, wait for a fixed port or DB migration) — read the relevant one for the exact command before running it. Every requirement below is real, not a pointer to go read something else first. For a specific agent's actual live content or progress — not just its status — invoke peeking-work instead of reading a pane/transcript inline here.
~/.straw-boss/capability.json records an explicit claude-p-only opt-out from init, if the user ever gave one. Its absence is not a hard stop and is not evidence herdr is unavailable — see Task 1's no-capability.json handling; claude-p dispatch never needed it.
Self-compact. The main agent can compact its own context anytime, on its own judgment, regardless of dispatch mode or whether a plan is involved — herdr agent prompt "$HERDR_PANE_ID" "/compact [focus]" types the command into its own pane; no separate tool or permission needed. It never needs to ask the user first. Reach for it once anything the next turn would need is already persisted somewhere durable (plan.json, an instruction file) rather than sitting only in this turn's own reasoning — full mechanics, including why this never interrupts work in flight, in cross-session-coordination.md's "Self-compact".
What ships with it
4 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.
- 3d ago First seen · 158 lines · 150 tokens per session scan A 5cbee5cec235
dispatching-work is a skill published in the GitHub repository wayne930242/straw-boss (3 stars, last pushed 3d ago), licensed MIT. It adds 150 tokens to every session and 4,780 once invoked, about $0.0007 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
agent-harness-fault-injection
Use when an agent workflow needs deterministic recovery evidence for sandbox, MCP/tool, worker, checkpoint, memory, or orchestration failures.
terraform-skill
Use when working with Terraform or OpenTofu - creating modules, writing tests (native test framework, Terratest), setting up CI/CD pipelines, reviewing configurations, choosing between testing approaches, debugging state issues, implementing security scanning (trivy, checkov), or making infrastructure-as-code…
xlsx
当电子表格文件是主要输入或输出时使用此技能。这意味着用户想要:打开、读取、编辑或修复现有的 .xlsx、.xlsm、.csv 或 .tsv 文件(例如添加列、计算公式、格式化、制图、清理混乱数据);从头创建新的电子表格或从其他数据源创建;或在表格文件格式之间进行转换。当用户通过名称或路径引用电子表格文件时特别触发——即使是随意提及(如"我下载目录里的 xlsx")——并且想对其进行操作或从中生成内容。也适用于将混乱的表格数据文件(格式错误的行、错位的表头、垃圾数据)清理或重构为规范的电子表格。交付物必须是电子表格文件。当主要交付物是 Word 文档、HTML 报告、独立 Python 脚本、数据库管道或 Google Sheets…
terraform-cli-setup
Terraform CLI 安装与初始化技能。当用户本地未安装 Terraform 时自动完成安装,确保 terraform 命令可用并能执行 init/validate。不负责 Provider 凭证配置,凭证在实际使用时由 terraform-skill 引导。.
agency-os
Notion-as-source-of-truth dispatch board for running your work like an AI agency. One Tasks database is the source of truth; tasks flow Suggestion through Discussion, To-Do, In Progress, and Done with subtasks, recurring cadences, dependencies, and template subtrees. Batch execution fans approved To-Do rows out to…
oma-scholar
Scholarly research companion using Knows sidecar spec (.knows.yaml). Generates, validates, reviews, queries, and compares structured research-paper sidecars, and fetches them from knows.academy. Use for academic literature search, survey synthesis, paper authoring assistance, and peer review with token-efficient…