task-list-viewer

task-list-viewer is a skill for Claude Code from paulbaranowski/wild-horses. It costs 129 tokens per session (2,185 once invoked), scanned A, original, MIT.

A read-only tool for inspecting JSON task lists used to track planned work. It can show overall progress, pending tasks, and the full details of a chosen task.

In plain words
What is it for?
Use it to see how many tasks are pending, which task is in progress, what remains, and where the matching Markdown plan is stored.
Why use it?
It lets you check a work plan without accidentally changing or running it. It also avoids opening and interpreting the task file by hand.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter.

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 harness plugin — 3 skills, 2 commands shipped together

Good fit Use it to see how many tasks are pending, which task is in progress, what remains, and where the matching Markdown plan is stored.

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 paulbaranowski/wild-horses
Claude Code
/plugin install harness

Made for: Claude Code.

Or install harness, the plugin that ships this one along with the rest of its 3 skills, 2 commands.

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 task-list-viewer

README.md
[![agentmods](https://agentmods.dev/badge/skills/paulbaranowski/wild-horses/task-list-viewer/github.svg)](https://agentmods.dev/skills/paulbaranowski/wild-horses/task-list-viewer)
Your own site
<a href="https://agentmods.dev/skills/paulbaranowski/wild-horses/task-list-viewer"><img src="https://agentmods.dev/badge/skills/paulbaranowski/wild-horses/task-list-viewer/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 task-list-viewer

Your own site · 80×15
<a href="https://agentmods.dev/skills/paulbaranowski/wild-horses/task-list-viewer"><img src="https://agentmods.dev/badge/skills/paulbaranowski/wild-horses/task-list-viewer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 129 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,185 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 $0.00129 $0.02185
Opus 5 $0.00064 $0.01092
Sonnet 5 $0.00026 $0.00437
Haiku 4.5 $0.00013 $0.00218

Measured 10d ago against content hash db1a17c0b6c4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

task-list-viewer 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 10d 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.

plugins/harness/skills/task-list-viewer/SKILL.md · 117 lines

How it starts

The opening of the file, as written. The whole thing — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.

task-list-viewer

Inspect a harness task list (JSON file matching the task-list-schema.md schema) without running, mutating, or building it. Pairs with task-list-builder (creates plans) and task-list-runner (executes them).

The schema this skill consumes is defined in ${CLAUDE_PLUGIN_ROOT}/task-list-schema.md. Re-read that file rather than relying on memory.

Arguments: $ARGUMENTS


CLI reference — task_list_cli.py

The bundled CLI at ${CLAUDE_PLUGIN_ROOT}/skills/task-list-runner/task_list_cli.py is the canonical interface to the task file. It lives in the runner's directory, not this skill's, on purpose — a single CLI keeps the viewer's interpretation of the file in lockstep with the runner's. Don't copy or shadow it here.

The viewer uses only the read-only verbs:

  • status — file-level metadata: counts (total, pending, in_progress, complete, failed), remaining integer, and plan path. Used both for Phase 2 candidate validation and for the Phase 3 summary header.
  • list [--status <s>] — full task array (or filtered by status). The viewer uses --status pending for the pending-titles list and --status in-progress to find the active task ID.
  • get --id <N> — pretty-printed single task. Used for the Phase 3 single-task detail view.

Every CLI invocation takes --file <task-file-path> first.

Don't invent verbs like view, inspect, show, or info — argparse rejects anything outside next, start, draft, publish, set-status, get, list, status, remaining, verify. The right read verb is always status, list, or get — the only three this skill calls.

Don't call mutation verbs (next, start, draft, publish, set-status, verify) from this skill, even though they're available. Viewing must not change the file. If the user asks "what should I work on next?" or "mark task 3 done" mid-session, point them at /task-list-runner (which atomically claims the next task) — don't invoke next here as a read.

Read the full file on GitHub · 117 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. 10d ago First seen · 117 lines · 129 tokens per session scan A db1a17c0b6c4

Subscribe to this mod's changes

task-list-viewer is a skill published in the GitHub repository paulbaranowski/wild-horses (12 stars, last pushed 22d ago), licensed MIT. It adds 129 tokens to every session and 2,185 once invoked, about $0.0006 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 2026-08-30.

Related

Other skills, from other repositories