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 skills add AkshitIreddy/agent-skills --skill finish-the-listgit clone --depth 1 https://github.com/AkshitIreddy/agent-skillsWrote 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/akshitireddy/agent-skills/finish-the-list)<a href="https://agentmods.dev/skills/akshitireddy/agent-skills/finish-the-list"><img src="https://agentmods.dev/badge/skills/akshitireddy/agent-skills/finish-the-list/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/akshitireddy/agent-skills/finish-the-list"><img src="https://agentmods.dev/badge/skills/akshitireddy/agent-skills/finish-the-list.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 | $0.00063 | $0.00814 |
| Opus 5 | $0.00032 | $0.00407 |
| Sonnet 5 | $0.00013 | $0.00163 |
| Haiku 4.5 | $0.00006 | $0.00081 |
Grade A, and why
finish-the-list 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 11d 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Finish the list
The failure this prevents: doing three items out of nine, writing a confident summary of the three, and calling the turn done. The summary is not the deliverable. The empty list is.
The rule
While an item remains and you can act on it, act on it. Do not stop to report, do not stop to ask whether to continue, do not stop because the turn has gone on a while. Stopping is for exactly three situations:
- The list is empty — every item is done, or explicitly recorded as not done with a reason.
- You are blocked on the user — proceeding under any assumption would be unsafe, destructive, or would make the work useless if the assumption is wrong. Not "I'd like confirmation"; genuinely blocked.
- The user told you to stop.
"I have done a good amount" is not one of them. Neither is "this is a natural checkpoint."
Before you stop, check the list again
The most common way this goes wrong is losing track of the list rather than deciding to abandon it. Before ending a turn, re-read the source of truth — the TODO file, the user's message, the issue list — and confirm every item is either done or recorded. Items get dropped when they were mentioned once, in the middle of a long message, and never written down.
Write the list down somewhere durable the moment you receive it. A list that only exists in the conversation is a list you will lose.
Order the work by what unblocks the most
Not by what is easiest. If one item is a foundation the others sit on (a shared constant, a type, a data structure), do it first — the alternative is doing the others twice.
Within that, prefer finishing an item completely over starting several. Half of each of four things is worth nothing; one finished thing is worth something.
Finishing means verified, not written
An item is done when you have evidence it works — the test passes, the screenshot shows it, the command exits zero. Not when the edit is saved. Code that compiles is not code that works, and a count that is correct is not a feature that is usable.
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.
- 11d ago First seen · 80 lines · 63 tokens per session scan A 33b91fcc1d4d
finish-the-list is a skill published in the GitHub repository AkshitIreddy/agent-skills (1 stars, last pushed 14d ago), licensed MIT. It adds 63 tokens to every session and 814 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
adhd-output-style
This skill should be used when the user asks for "ADHD output", "fewer output tokens", "short numbered steps", "limited working memory formatting", or explicitly invokes "adhd-output-style".
lov-organize-storage
A storage-organization tool for surveying a whole drive or archive and planning a project-based folder layout. It can rename items within the same drive after confirmation, while keeping a mapping, log, and rollback script.
lov-personal-vocabulary
A manager for one shared personal vocabulary list that can be reused across voice-input apps.
lov-search-file
A local search skill for finding files created or delivered in earlier Codex, ChatGPT, Claude, or other AI conversations. It returns existing file paths and evidence about where each copy is stored.
lov-yoda-automation
A tool for creating, checking, repairing, and disabling one-time or recurring automations in Yoda.
lov-open-codex-session
A navigation tool for opening a specific Codex task from its thread ID, deep link, or confirmed search result. Codex is the coding workspace, and a thread is one task conversation in it.