A read-only delivery board built from GitHub Issues and pull requests, showing work that is ready, claimed, under review, blocked, or awaiting people.

Use it to inspect task labels, assignments, pull-request reviews, and CI status; with reclamation enabled, it can reconcile labels and release stale claims.

It gives a single view of delivery state and highlights stale claims, review changes, failed checks, and work that needs human attention.

task-status — Skill by blakemartz

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.

agentmods

npx agentmods add skills/blakemartz/delivery-loop/task-status

Any agent

npx skills add blakemartz/delivery-loop --skill task-status

Clone the repo

git clone --depth 1 https://github.com/blakemartz/delivery-loop

Made for: Claude Code, Codex.

Per session 48 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 453 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

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.

Model	Per session	Once invoked
Fable 5	$0.00048	$0.00453
Opus 5	$0.00024	$0.00227
Sonnet 5	$0.00010	$0.00091
Haiku 4.5	$0.00005	$0.00045

Measured yesterday against content hash 6193afa72f28, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

task-status 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 yesterday.

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.

plugins/delivery-loop/skills/task-status/SKILL.md · 28 lines

What it actually says

task-status — board overview (+ reclamation)

You are the board renderer (and with --reclaim, the reclamation actuator) from the delivery spec (${CLAUDE_PLUGIN_ROOT}/docs/agentic_delivery_spec.md, §5).

Protocol

If invoked with --reclaim: run bash "${CLAUDE_PLUGIN_ROOT}/scripts/task-queue.sh" --fix (reconciles blocked/ready labels, releases stale agent claims >4h idle with no PR, pings stale human claims >72h, and auto-closes fully-delivered epics). Report every fix: line it emits. Otherwise run bash "${CLAUDE_PLUGIN_ROOT}/scripts/task-queue.sh" (read-only).
Gather the rest of the board:
- gh issue list --label task --state open --limit 200 --json number,title,labels,assignees,updatedAt
- gh issue list --label needs-human --state open --json number,title
- gh pr list --state open --json number,title,labels,statusCheckRollup,reviewDecision
Render one compact table per bucket, in this order (most actionable first):
- needs-human — issue, what's stuck (from the latest comment)
- approved, awaiting human merge — PR, linked issue
- changes-requested — PR, iteration count
- in-review — PR, CI status, review state
- claimed — issue, assignee, human-or-agent, idle time
- ready — the queue output, in order
- blocked — issue, which unmet deps
End with a one-line "next action" suggestion: what a single delivery-tick would do right now.

Read-only apart from --reclaim. Never claim, review, or edit anything else here.

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.

yesterday First seen · 28 lines · 48 tokens per session scan A 6193afa72f28

Subscribe to this mod's changes

task-status is a skill published in the GitHub repository blakemartz/delivery-loop (4 stars, last pushed 1mo ago), licensed MIT. It adds 48 tokens to every session and 453 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.

Code review DevOps and cloud Git and workflow agentic ai-agents claude-code claude-code-plugin developer-tools

zh-output-example

Reviews Chinese skill documentation for publication readiness. Invoke when the user asks in Chinese to review a skill.

bytedance/deer-flow · 24 tokens

peekaboo

Capture and automate macOS UI with the Peekaboo CLI.

the-open-agent/openagent · 17 tokens

powerpoint

Create designed, editable PowerPoint .pptx presentations with PptxGenJS. Use when the user asks to create, generate, update, or inspect a deck, slide deck, presentation, or .pptx file.

the-open-agent/openagent · 48 tokens

oracle

Best practices for using the oracle CLI (prompt + file bundling, engines, sessions, and file attachment patterns).

the-open-agent/openagent · 25 tokens

argent-tv-interact

Control and inspect TV apps via argent — Apple TV (tvOS), Android TV (leanback), and Amazon Fire TV (Vega). Boot the target, read focus, navigate with the D-pad remote, type, screenshot, and on Vega debug the JS runtime (evaluate, console logs, network inspector). Use when a task targets a TV (runtimeKind "tv", or…

software-mansion/argent · 107 tokens

review-offered-task

Review a task that has been offered to you and decide whether to accept or reject it.

desplega-ai/agent-swarm · 22 tokens