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 jackfranklin/dotfiles --skill one-by-onegit clone --depth 1 https://github.com/jackfranklin/dotfilesWrote 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/jackfranklin/dotfiles/one-by-one)<a href="https://agentmods.dev/skills/jackfranklin/dotfiles/one-by-one"><img src="https://agentmods.dev/badge/skills/jackfranklin/dotfiles/one-by-one/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/jackfranklin/dotfiles/one-by-one"><img src="https://agentmods.dev/badge/skills/jackfranklin/dotfiles/one-by-one.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 13 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Excessive Agency · line 49 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.01034 |
| Opus 5.5 | $0.00025 | $0.00414 |
| Sonnet 5.5 | $0.00013 | $0.00207 |
| Haiku 4.5 | $0.00006 | $0.00103 |
Grade A, and why
one-by-one 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 1mo 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 — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
One-by-One
Guide the user through a list of findings interactively, one at a time. Each finding gets its own focused conversation: context, background, the problem it points to, and options for what to do about it. Do not rush ahead or present the next item until the user is done with the current one.
Your role
- Orient first. At the start, briefly acknowledge how many items you're working through and start with item 1. Don't ask the user if they want to begin — they already invoked the skill.
- One finding at a time. Present each finding fully, then end with the closing prompt and wait for the user to respond before moving on.
- Give real context. Don't just restate the finding. Explain why it matters: what could go wrong, what pattern it violates, what it makes harder to maintain or change. Reference the relevant code if you have it.
- Offer concrete paths forward. Give one option if there is genuinely only one reasonable path — that's a valid answer, not a shortcut. Don't reduce to one option just because you have a preference; if the options represent meaningfully different approaches or trade-offs, present them separately. Give two or three when trade-offs genuinely depend on context or constraints — but only count options that represent meaningfully different paths; don't pad. Beyond three genuinely distinct options, you're doing the user's sorting work for them — collapse them and strengthen your recommendation instead. Be specific — name the function, change, or pattern, not vague advice like "refactor this". If you have questions for the user (e.g. about intent or constraints), ask them before presenting options.
- Handle mid-finding dialogue. If you asked a scoping question and the user answers, or if the user asks a follow-up rather than making a decision, respond and continue the conversation within the same finding. Only advance to the next finding when the user has made a clear decision (fix, defer, or dismiss). Re-present the options in the format block if the scoping answer changes what you'd recommend.
- Honour the user's decision. The user may want to fix it, defer it, dismiss it, or discuss it further. Accept any of these and move on.
- Track position. Always make clear which finding you're on (e.g. "Finding 2 of 7") so the user knows where they are.
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.
- 1mo ago First seen · 54 lines · 63 tokens per session scan A bd7e1d87c27c
one-by-one is a skill published in the GitHub repository jackfranklin/dotfiles (254 stars, last pushed 6d ago), licensed MIT. It adds 63 tokens to every session and 1,034 once invoked, about $0.0003 per session on Opus 5.5. 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
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…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
component-fixtures
Use when creating or updating component fixtures for screenshot testing or their shared infrastructure, or when designing UI components to be fixture-friendly. Covers fixture file structure, theming, service setup, CSS scoping, async rendering, validation, and common pitfalls.