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.
/plugin marketplace add paulbaranowski/wild-horses/plugin install harnessWrote 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.
[](https://agentmods.dev/skills/paulbaranowski/wild-horses/task-list-builder)<a href="https://agentmods.dev/skills/paulbaranowski/wild-horses/task-list-builder"><img src="https://agentmods.dev/badge/skills/paulbaranowski/wild-horses/task-list-builder/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.
<a href="https://agentmods.dev/skills/paulbaranowski/wild-horses/task-list-builder"><img src="https://agentmods.dev/badge/skills/paulbaranowski/wild-horses/task-list-builder.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 5.1 | $0.00100 | $0.05008 |
| Opus 5 | $0.00050 | $0.02504 |
| Sonnet 5 | $0.00020 | $0.01002 |
| Haiku 4.5 | $0.00010 | $0.00501 |
Grade A, and why
task-list-builder 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 9d 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.
How it starts
The opening of the file, as written. The whole thing — 311 lines — stays where its author put it; the contents beside it link to each section on GitHub.
task-list-builder
Build a paired .json + .md task list in the format the harness loop runner consumes.
The schema is defined in ${CLAUDE_PLUGIN_ROOT}/task-list-schema.md. That file is the source of truth — do not duplicate the schema here, read it.
Arguments: $ARGUMENTS
Phase 0 — Parse meta-flags
Two optional flags can appear anywhere in $ARGUMENTS. Strip them before any other phase parses arguments.
--slug <name>— overrides the defaulttask-list-builderfilename suffix. The output paths become…<short-description>.<name>.{json,md}instead of…<short-description>.task-list-builder.{json,md}. Validate that<name>matches[a-z][a-z0-9-]*(lowercase letters, digits, hyphens; must start with a letter). If validation fails, refuse and ask the user for a valid slug.--md-body-from-context— when writing the MD file in Phase 6, use the most recent rendered analysis report from the current conversation as the MD body (instead of synthesizing a generic body). Carries through to Phase 6.
After stripping, what remains is the input source for Phase 1.B (path / free-form / empty).
Typical caller patterns:
- User running standalone: no flags. Default slug, generated MD body.
/harness:feedback-blockersPhase 4:--slug feedback-blockers --md-body-from-context. The merged Phase 3 report is in conversation; the slug preserves provenance./harness:reasoning-gapsPhase 4:--slug reasoning-gaps --md-body-from-context. Same shape.
Phase 1 — Detect the output target and the content source
These are two independent decisions. Make both before continuing.
A. Output target: fresh build vs. in-place rewrite
It's an in-place rewrite if any of these are true:
$ARGUMENTScontains a path ending in.jsonAND the file exists.- The user's phrasing includes "rewrite", "update", or "regenerate" + a reference to an existing plan/task file (e.g., "rewrite the plan file using task-list-builder").
What ships with it
2 files 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.
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.
- 9d ago First seen · 311 lines · 100 tokens per session scan A 9b4bf9d04d1b
task-list-builder is a skill published in the GitHub repository paulbaranowski/wild-horses (12 stars, last pushed 21d ago), licensed MIT. It adds 100 tokens to every session and 5,008 once invoked, about $0.0005 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…