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 TweekFawkes/prompts --skill z_sortgit clone --depth 1 https://github.com/TweekFawkes/promptsWrote 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/tweekfawkes/prompts/z_sort)<a href="https://agentmods.dev/skills/tweekfawkes/prompts/z_sort"><img src="https://agentmods.dev/badge/skills/tweekfawkes/prompts/z_sort/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/tweekfawkes/prompts/z_sort"><img src="https://agentmods.dev/badge/skills/tweekfawkes/prompts/z_sort.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 | $0.00138 | $0.01213 |
| Opus 5 | $0.00069 | $0.00607 |
| Sonnet 5 | $0.00028 | $0.00243 |
| Haiku 4.5 | $0.00014 | $0.00121 |
Grade A, and why
z_sort scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- Read-only inspection of environments (`curl`, `dig`, DB reads, log reads). How it starts
The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/z_sort — Sort open tickets into agent-doable vs human-needed
You are triaging the backlog. For every open ticket, decide whether the agent (you) can carry it from start to finish with zero help from a human, and physically move the file into the matching folder.
- Sort, don't implement. This skill only classifies and moves files — it does NOT do the ticket work. (That's
/dowork.)
Authoritative paths
- Project root: the current working directory.
- Source:
z_tickets/open/*.md - Destinations:
z_tickets/open_agent/andz_tickets/open_human/
Create both destination folders if missing (mkdir -p). Ignore files whose names start with _ or ..
The decision rule
A ticket goes to open_human if completing it (closing it fully, not just advancing it) requires any of the following — i.e. anything the agent cannot or must not do alone:
- A production mutation. Treat production as gated. Any prod deploy, prod DNS cutover, prod env/secret change, prod data change, or an "explicit user confirmation before prod" requirement → human. (Adjust to your project's policy — e.g. dev pre-authorized, test/staging not gated.)
- An out-of-band / external party. Anything that needs someone else to act — e.g. an API-key owner, a domain registrar, a third-party support desk, or a credential the agent doesn't hold.
- A console/dashboard-only action with no API/CLI path. E.g. a change that can only be made by clicking through a third-party web dashboard → must be done by a human.
- An explicit human-approval gate written into the ticket ("pause for user confirmation", "gated", "do not do autonomously"), or an irreversible/destructive step the ticket says to confirm first.
- A judgment call reserved for the user — a product/policy decision the ticket leaves open.
Otherwise the ticket goes to open_agent: the agent can do every remaining step alone. Things the agent CAN typically do without a human:
- Dev work of any kind, plus non-gated test/staging deploys and verification.
- Read-only inspection of environments (
curl,dig, DB reads, log reads). - Code changes, tests, lint/build, smoke tests, opening PRs.
- Local file/git operations, env-file hygiene on dev.
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 · 63 lines · 138 tokens per session scan A 896f83afe375
z_sort is a skill published in the GitHub repository TweekFawkes/prompts (2 stars, last pushed 1mo ago), licensed Unlicense. It adds 138 tokens to every session and 1,213 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
recipe-create-meet-space
Create a Google Meet meeting space and share the join link.
workthreads
SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…
atmos-config
Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.
story-readiness
Validate that a story file is implementation-ready. Checks for embedded GDD requirements, ADR references, engine notes, clear acceptance criteria, and no open design questions. Produces READY / NEEDS WORK / BLOCKED verdict with specific gaps. Use when user says 'is this story ready', 'can I start on this story', 'is…
autotask-creator
Rules for automation CRUD from the group-chat commander. The commander does not call mutation tools and does not edit cloud/autotasks files directly. It emits one or more top-level ... containers in its final text; the bus parses and applies them after the turn.
projects
List all managed projects with status, branch, open PRs, and open issue counts — portfolio-level view.