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.
npx agentmods add skills/hlalljie/agent-workflow-presets/run-task-loopnpx skills add hlalljie/agent-workflow-presets --skill run-task-loopgit clone --depth 1 https://github.com/hlalljie/agent-workflow-presetsWrote 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/hlalljie/agent-workflow-presets/run-task-loop)<a href="https://agentmods.dev/skills/hlalljie/agent-workflow-presets/run-task-loop"><img src="https://agentmods.dev/badge/skills/hlalljie/agent-workflow-presets/run-task-loop.svg" alt="Measured on agentmods" 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 | $0.00058 | $0.01241 |
| Opus 5 | $0.00029 | $0.00620 |
| Sonnet 5 | $0.00012 | $0.00248 |
| Haiku 4.5 | $0.00006 | $0.00124 |
Grade A, and why
run-task-loop 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 4d 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Run task loop
Goal
Finish the work with strong coverage, without owner involvement until done, blocked, or out of credible fixes.
Doc shape: This skill points at other skills (add-tests, run-tests, verify-commit) instead of inlining every instruction—modular by choice; if that becomes hard to follow, a future option is one consolidated runbook.
Stop only for
- Blocker — decision, access, ambiguity, or rule that forbids proceeding (dependency-safety.mdc, data-safety.mdc, …).
- Owner-only items in
open-questions.md, plan, or tasks. - No viable path after reasonable retries.
Otherwise keep going.
First action: blockers
- Scan conversation, plan,
open-questions.md, tasks for owner-only items. - If blocking → list and stop; else proceed.
Task list (always a step)
The task file may already exist or not yet—either way, this step runs:
- If there is no task file for the current scope: create one with create task list under
.cursor/plans/**/tasks/*.md. - If it exists: open it and work from
### Task Nin sequence.
Do not skip this step; scope and checkboxes live there.
Task cadence
Overrides default one-task-per-message in task-scope.mdc: in this invocation, implement Task 1, 2, 3… in order until the feature is done, you hit Stop only for, or Handoff—not only the first task.
Build loop
- Codebase survey (MANDATORY before any code) — Before writing any file or editing any component, read the existing codebase for the area you are touching:
- Read
docs/folder-structure.mdfor the canonical map of what lives where. - Read the reference implementation identified in
.cursor/rules/repository-layout.mdc— the closest existing route, module, or component of the same type as what you're building. - Read any shared primitives (layout, shell, utilities) relevant to the task before creating new ones.
- Match the patterns you find. Do not invent new folder names, new structural conventions, or new abstraction layers unless the task explicitly requires it and you explain why.
- This step is not optional and cannot be skipped for speed. Producing code that doesn't match existing structure creates more rework than doing it right.
- Read
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.
- 4d ago First seen · 76 lines · 58 tokens per session scan A 245aab8fb66e
run-task-loop is a skill published in the GitHub repository hlalljie/agent-workflow-presets (2 stars, last pushed 1mo ago), licensed MIT. It adds 58 tokens to every session and 1,241 once invoked, about $0.0003 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.
Other skills, from other repositories
curate-a-team-library
Use when building a managed team skills library for a real stack. Map work to shelves, browse before curating, write meaningful whyHere notes, and create a starter pack once the first pass is solid.
migrate-skills-between-libraries
Use when moving skills between library workspaces or upgrading from a personal library to a team library. Export from one workspace, import into another.
review-a-skill
Use when evaluating whether a skill belongs in a library. Preview content, check frontmatter, validate structure, and decide whether to keep, curate, or remove.
audit-library-health
Use when checking the overall health of a skills library. Run doctor, validate, check for stale skills, and verify generated docs are in sync.
browse-and-evaluate
Use when exploring the ai-agent-skills catalog to find, compare, and evaluate skills before installing. Always use --fields to limit output size and --dry-run before committing to an install.
install-from-remote-library
Use when installing skills from a shared ai-agent-skills library repo. Inspect with --list first, prefer --collection, and preview with --dry-run before installing.