boss-say

boss-say is a skill for Claude Code from wayne930242/straw-boss. It costs 41 tokens per session (3,469 once invoked), scanned A, original, MIT.

A routing guide for Straw Boss, a system that assigns software work to the appropriate specialist skill or coding agent. It selects how much coordination a task needs and how agents should work together.

In plain words
What is it for?
Use it for one task, a small independent batch, or a backlog. It can route work to skills for shipping, application inspection, investigation, or troubleshooting.
Why use it?
It prevents every task from using the same heavy process and helps send work to the right specialist.

Skill for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: mentions subagents; mentions Codex.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the straw-boss plugin — 17 skills, 2 hooks shipped together

Good fit Use it for one task, a small independent batch, or a backlog. It can route work to skills for shipping, application inspection, investigation, or troubleshooting.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add wayne930242/straw-boss
Claude Code
/plugin install straw-boss

Made for: Claude Code.

Or install straw-boss, the plugin that ships this one along with the rest of its 17 skills, 2 hooks.

Wrote 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.

agentmods badge for boss-say

README.md
[![agentmods](https://agentmods.dev/badge/skills/wayne930242/straw-boss/boss-say/github.svg)](https://agentmods.dev/skills/wayne930242/straw-boss/boss-say)
Your own site
<a href="https://agentmods.dev/skills/wayne930242/straw-boss/boss-say"><img src="https://agentmods.dev/badge/skills/wayne930242/straw-boss/boss-say/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.

agentmods 80×15 button for boss-say

Your own site · 80×15
<a href="https://agentmods.dev/skills/wayne930242/straw-boss/boss-say"><img src="https://agentmods.dev/badge/skills/wayne930242/straw-boss/boss-say.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 41 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,469 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00041 $0.03469
Opus 5 $0.00020 $0.01734
Sonnet 5 $0.00008 $0.00694
Haiku 4.5 $0.00004 $0.00347

Measured 5d ago against content hash fb6680d14426, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

boss-say 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.

skills/boss-say/SKILL.md · 125 lines

How it starts

The opening of the file, as written. The whole thing — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Overview

This skill owns routing and capped-batch scheduling. Domain work stays with its specialist: shipping-task, inspecting-app, investigating-app, or troubleshooting-app. work-on resolves the app; dispatching-work supplies mechanics only when a separate workroom is useful.

Choose the smallest sufficient execution tier. The process is light when its coordination cost stays below the work it coordinates. Once work is dispatched, the user and dispatched agent choose the specification, design, implementation, and the verification method inside the named reality anchor.

Branch: Receiving an orchestrator handoff

When the incoming prompt names an Orchestrator handoff file, read that offered continuity record and route its single transferred scope through Task 1. After the owner, coordination graph, and reality anchor are established, record acceptance from this receiving pane before implementation continues:

uv run --script "${CLAUDE_PLUGIN_ROOT}/scripts/accept-orchestrator-handoff.py" \
  --handoff-path <path> --owner <owning-skill> \
  --coordination-graph '<graph>' --reality-anchor '<anchor>'

Those structured route facts are the acceptance record. Use the owner, graph, and anchor actually established in Task 1; the source validates all three before transferring ownership.

The source already obtained approval for this window. Use the record's excluded scopes as ownership boundaries; ask only a new work decision that the routed task itself genuinely needs.

Branch: A skill is named right after the trigger phrase

For boss say <skill> <work>, resolve a clear name, abbreviation, or partial match and invoke that skill with <work>. State a genuine ambiguity or missing match. A multi-item batch still follows the batch path below, using the named skill as each item's owner.

Task 1: Triage scale and execution tier, then pick the dispatch shape

Collect the items, select the owning skill, and state the shape with one reason.

Read the full file on GitHub · 125 lines

Changes

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.

  1. 5d ago Changed · +21 lines fb6680d14426
  2. 10d ago First seen · 104 lines · 41 tokens per session scan A 8c0682126fd0

Subscribe to this mod's changes

boss-say is a skill published in the GitHub repository wayne930242/straw-boss (4 stars, last pushed today), licensed MIT. It adds 41 tokens to every session and 3,469 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.

Related

Other skills, from other repositories

create-request

Create, update, or scan per-task request tickets for progress tracking. These are date-prefixed non-lifecycle docs under requests/, NOT feature-level requirements (use /req-analyze for those). Use when: tracking task progress, updating completion status, scanning incomplete requests, checking request status dashboard.…

sd0xdev/sd0x-harness · 112 tokens

req-analyze

A requirements-analysis tool that breaks a problem into needs, stakeholders, and priorities before a technical solution is chosen.

sd0xdev/sd0x-harness · 101 tokens

recap-ask

Interactive Q&A over an existing recap document. Use when: user wants to ask follow-up questions about a briefing-recap- .md produced by /recap-doc, with recap-bounded context + out-of-scope redirect + optional promote-to-request. Not for: generating a new recap (use /recap-doc), general project Q&A (use /ask), code…

sd0xdev/sd0x-harness · 106 tokens

recap-doc

Post-development recap document generator. Use when: AI/Codex has implemented a feature and the user needs a guided walkthrough of what changed and why, with blind-spot detection and anticipated questions. Not for: Q&A follow-up (use /recap-ask), technical share-out for teammates (use /tech-brief), or generic code…

sd0xdev/sd0x-harness · 114 tokens

runbook

Generate and update feature release runbooks from existing docs and codebase. Use when: creating operational runbook, release handbook, deployment checklist, pre-release preparation. Not for: incident response (v2), code review (use codex-code-review), architecture design (use architecture).

sd0xdev/sd0x-harness · 59 tokens

jira

Jira integration — view issues, generate branches, create tickets, transition status. Use when: user mentions Jira ticket key (XX-123), says /jira, wants to create branch from ticket, create a new ticket, or update Jira status. Not for: GitHub issues (use issue-analyze).

sd0xdev/sd0x-harness · 64 tokens