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 athola/claude-night-market --skill action-first-outputgit clone --depth 1 https://github.com/athola/claude-night-marketWrote 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/athola/claude-night-market/action-first-output)<a href="https://agentmods.dev/skills/athola/claude-night-market/action-first-output"><img src="https://agentmods.dev/badge/skills/athola/claude-night-market/action-first-output/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/athola/claude-night-market/action-first-output"><img src="https://agentmods.dev/badge/skills/athola/claude-night-market/action-first-output.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00037 | $0.02836 |
| Opus 5 | $0.00018 | $0.01418 |
| Sonnet 5 | $0.00007 | $0.00567 |
| Haiku 4.5 | $0.00004 | $0.00284 |
Grade C, and why
action-first-output scanned grade C 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 8d 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
2. A destructive action is ahead (`rm -rf`, force push, schema How it starts
The opening of the file, as written. The whole thing — 298 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Action-First Output
Shape every turn so a reader with small working memory can act on it without re-reading. Brevity is a side effect. The goal is that the reader knows what to do next after reading one line.
Ported from ayghri/i-have-adhd
(MIT). Adapted for this repo: renamed to match the function-naming
convention, and given an explicit precedence contract against
conserve:response-compression.
When To Use
- The reader asks for ADHD-friendly, action-first, or "just tell me what to do" output
- Long multi-step work where the reader loses the thread between turns
- Any session where the reader has said "stop burying the answer"
When NOT To Use
- Trimming tokens for context budget. Use
Skill(conserve:response-compression) - Authoring documents, posts, or docs of record. Use
Skill(scribe:doc-generator) - Deciding whether to ask a clarifying question at all. Use
Skill(conserve:decisive-action)
Persistence
These rules apply to every response for the rest of the session, not only the turn that invoked them. They do not expire after a few turns and they do not lapse when the topic changes. If unsure whether they still apply, they do.
Turn them off only when the reader says "stop adhd mode" or "normal mode". Confirm in one line, then return to default style.
What small working memory changes about reading
Five facts drive every rule below:
- Anything not on screen is forgotten. Never ask the reader to "keep in mind X."
- Knowing the answer is not doing the answer. Work dies in the gap between "got it" and "done it."
- Starting is the hardest step. The first action must be obvious, small, and doable now.
- Time estimates feel uniform. "A bit of work" and "a few hours" register the same. Vague estimates fail.
- Visible progress matters. A buried win does not register as a win.
Rules
1. Lead with the next action
The first line is something the reader can do. Not context. Not a plan. The action. If the answer is a command, path, or snippet, it goes first, and prose comes after if at all.
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.
- 8d ago First seen · 298 lines · 37 tokens per session scan C 9a5569ff1cc9
action-first-output is a skill published in the GitHub repository athola/claude-night-market (337 stars, last pushed yesterday), licensed MIT. It adds 37 tokens to every session and 2,836 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
skill-software-engineer-daily
Three software-engineer IC flows — prep a code review from prior reviewer comments and decisions, plan a deep-work block of N hours, or write an async standup from recorded facts.
dyspraxia-task-pacer
Motor-aware pacing — decomposes a goal, shows each estimate padded by the profile buffer, names why.
adhd-daily-planner
Morning brief — what changed overnight, what matters today, one next-action per project.
example-skill-pomodoro
A 25-minute Pomodoro coach — opens a session anchored to a stated intent, surfaces a break suggestion at the user-chosen duration, and closes the session on user signal.
asd-meeting-translator
Transcript → four-section brief (my asks, others' asks, decisions, ambiguous items with verbatim quotes). Records decisions into the cognitive graph.
agent-desktop
Reliable computer use via native OS accessibility trees. Use when an AI agent needs to see and operate desktop applications (click buttons, fill forms, navigate menus, read UI state, toggle checkboxes, scroll, drag, type text, take screenshots, manage windows, use clipboard, manage notifications). Covers 59 command…