tasks

A task-backlog status view for showing pending, active, blocked, overdue, and recently completed work.

In plain words
What is it for?
Use it to check what is being worked on, what is late or blocked, which pending tasks have the highest priority, and which tasks have attached documents.
Why use it?
It gathers task information into one concise overview, so you do not have to inspect each task or filter manually.

Skill for Claude CodeCodex

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/backloghq/backlog/tasks
Any agent
npx skills add backloghq/backlog --skill tasks
Clone the repo
git clone --depth 1 https://github.com/backloghq/backlog

Made for: Claude Code, Codex.

Per session 39 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 296 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.

ModelPer sessionOnce invoked
Fable 5 $0.00039 $0.00296
Opus 5 $0.00019 $0.00148
Sonnet 5 $0.00008 $0.00059
Haiku 4.5 $0.00004 $0.00030

Measured 2d ago against content hash 0339570d7f06, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

tasks 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 2d 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/tasks/SKILL.md · 18 lines

What it actually says

Task Status Overview

Show the current state of the task backlog. Use the backlog MCP tools to query and present the following:

  1. Active tasks — call task_list with filter +ACTIVE to show tasks currently being worked on
  2. Overdue tasks — call task_list with filter +OVERDUE to show tasks past their due date
  3. Blocked tasks — call task_count with filter +BLOCKED status:pending to count blocked tasks
  4. Pending tasks by priority — call task_list with filter status:pending and group results by priority (H, M, L, none)
  5. Tasks with docs — call task_count with filter +doc status:pending to count tasks with attached specs/docs
  6. Recently completed — call task_list with filter status:completed end.after:now-7d to show work done in the last 7 days

Present the results in a concise, scannable format. Skip sections that have zero results. If the backlog is completely empty, say so and suggest using /backlog:plan to create tasks.

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. 2d ago First seen · 18 lines · 39 tokens per session scan A 0339570d7f06

Subscribe to this mod's changes

tasks is a skill published in the GitHub repository backloghq/backlog (5 stars, last pushed 3mo ago), licensed MIT. It adds 39 tokens to every session and 296 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.