peeking-work

peeking-work is a skill for Claude Code from wayne930242/straw-boss. It costs 48 tokens per session (778 once invoked), scanned A, original, MIT.

A read-only skill for checking the live progress of a dispatched coding task without joining or interrupting it. A dispatched task is work assigned to another coding session or workspace.

In plain words
What is it for?
Reading progress logs, task status, live pane information, and recent transcript output for a dispatched task.
Why use it?
It shows what a task is doing and helps identify whether it is stuck or has failed without changing its work.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the straw-boss plugin — 16 skills, 2 hooks shipped together

Good fit Reading progress logs, task status, live pane information, and recent transcript output for a dispatched task.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/wayne930242/straw-boss/peeking-work
Install

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.

Any agent
npx skills add wayne930242/straw-boss --skill peeking-work
Clone the repo
git clone --depth 1 https://github.com/wayne930242/straw-boss

Made for: Claude Code.

Or install straw-boss, the plugin that ships this one along with the rest of its 16 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 peeking-work

README.md
[![agentmods](https://agentmods.dev/badge/skills/wayne930242/straw-boss/peeking-work.svg)](https://agentmods.dev/skills/wayne930242/straw-boss/peeking-work)
Your own site
<a href="https://agentmods.dev/skills/wayne930242/straw-boss/peeking-work"><img src="https://agentmods.dev/badge/skills/wayne930242/straw-boss/peeking-work.svg" alt="Measured on agentmods" height="20"></a>
Per session 48 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 778 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 $0.00048 $0.00778
Opus 5 $0.00024 $0.00389
Sonnet 5 $0.00010 $0.00156
Haiku 4.5 $0.00005 $0.00078

Measured 7d ago against content hash b0c1c2ca20f1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

peeking-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 7d 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/peeking-work/SKILL.md · 48 lines

How it starts

The opening of the file, as written. The whole thing — 48 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Overview

Read-only. Never interrupts a working pane, never sends input, never substitutes for the actual checkpoint-answering flow — it only tells you what a dispatched task is currently doing. Every straw-boss skill that needs this reads it through here; the pane-read, progress-trail, and transcript-tail mechanics are not reimplemented inline anywhere else.

Task 1: Resolve the target dispatch

Identify which dispatch to peek at from a task id/plan slug, session id, or description. Resolve the canonical instruction at ~/.straw-boss/dispatch/<app>--<slug>.json; for a plan task, use its plan_id/task_id correlation rather than treating the status record as routing data. The instruction supplies mode, session_id, and repo_root. For herdr-pane, its launch receipt supplies the agent name and pane. Ask the caller when more than one instruction matches.

Verification: the target dispatch is confirmed from its actual instruction/status file, not guessed from a name alone.

Task 2: Read the progress trail first

Before touching the live pane or transcript, read the dispatch's own progress log — a sibling <app>--<slug>.progress.jsonl next to its instruction file (per dispatch-mechanics.md's "Reporting scripts"), written by the dispatched agent's own report-progress.py calls throughout its work. Tail it (most recent few entries) rather than dumping the whole file. For a plan task, also check its status file — a terminal or checkpoint status there answers the question outright.

If the trail (plus, for a plan task, the status file) already answers "what's it doing" — a recent note, a clear status — that's your answer; skip Task 3 entirely. This is the whole point of the trail existing: most peeks shouldn't need to join the dispatched agent's live pane at all.

Verification: the trail was checked before any live read was attempted; a peek that the trail already answered did not also do a live read "just to be thorough."

Task 3: Peek live, only when the trail doesn't answer it

Read the full file on GitHub · 48 lines

Files

What ships with it

1 file 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.

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. 7d ago First seen · 48 lines · 48 tokens per session scan A b0c1c2ca20f1

Subscribe to this mod's changes

peeking-work is a skill published in the GitHub repository wayne930242/straw-boss (3 stars, last pushed 3d ago), licensed MIT. It adds 48 tokens to every session and 778 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