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 IgorWarzocha/howaboua-pi-stuff --skill agents-mdgit clone --depth 1 https://github.com/IgorWarzocha/howaboua-pi-stuffWrote 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/igorwarzocha/howaboua-pi-stuff/agents-md)<a href="https://agentmods.dev/skills/igorwarzocha/howaboua-pi-stuff/agents-md"><img src="https://agentmods.dev/badge/skills/igorwarzocha/howaboua-pi-stuff/agents-md.svg" alt="Measured on agentmods" 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 | $0.00018 | $0.00612 |
| Opus 5 | $0.00009 | $0.00306 |
| Sonnet 5 | $0.00004 | $0.00122 |
| Haiku 4.5 | $0.00002 | $0.00061 |
Grade A, and why
agents-md 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 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.
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.
What it actually says
- Inspect the target scope, applicable ancestor files, relevant nested files, and only enough code or configuration to verify proposed guidance.
- Establish whether the target is an ordinary brownfield root, a nested subtree, greenfield product guidance, or personal and global policy.
- Put each rule in its nearest durable home.
- Prefer code, configuration, or an executable check when it can enforce the rule.
- Keep human-facing explanation in README or appropriate documentation.
- Use
AGENTS.mdfor non-obvious intent, constraints, hazards, ownership boundaries, and pointers that change what an agent should load or do. - Create a nested file only for a genuine local delta: subtree ownership, public API or import boundaries, generated or frozen areas, required wrappers or local tools, placement traps, subtree-only skills or documentation, and recurring mistakes an agent cannot cheaply infer.
- Do not use nested files for task history, implementation summaries, directory tours, or repeated ancestor guidance.
- Start the target file with its first useful rule or scope statement. Address the reading agent as you. Do not add a filename heading, purpose preamble, frontmatter, or wrapper unless the target harness requires it.
- Match the register to the scope.
- Ordinary brownfield roots and nested files use compact, machine-first bullets or unambiguous fragments.
- Personal and global files, including personal agent repositories, may use first-person prose, humour, metaphor, and distinctive voice when the language carries identity, relationship, taste, autonomy, permission boundaries, or collaboration style.
- Greenfield guidance may preserve expressive founder language when it controls product decisions that code cannot yet encode.
- Keep expressive passages specific and decision-bearing. Remove generic inspiration, performed personality, and decorative flourishes that change nothing.
- Do not inventory the stack, source tree, package scripts, routine commands, task history, or behaviour cheaply visible in code and configuration. Include a command only when its selection, timing, wrapper, exception, or danger changes agent behaviour.
- Preserve user-authored intent and local terminology. When deletion could weaken ambiguous root, global, or personal policy, keep it or ask rather than silently deciding.
- Verify paths, commands, ownership, tool names, and claimed conventions locally. Do not promote guesses, one-off observations, or current-task details into standing rules.
- Aim ordinary brownfield roots at roughly 20 lines and nested files at 1 to 10. Treat more than 40 ordinary repo lines as suspicious and more than 100 as misplaced documentation unless strong context proves otherwise. Allow longer greenfield and personal files when they carry durable intent unavailable elsewhere.
- Finish when every retained line changes behaviour, preserves intent, or routes necessary context, facts match repository truth, and nested guidance is only a scoped delta.
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 · 26 lines · 18 tokens per session scan A 4acaa55d7740
agents-md is a skill published in the GitHub repository IgorWarzocha/howaboua-pi-stuff (358 stars, last pushed today), licensed MIT. It adds 18 tokens to every session and 612 once invoked, about $0.0001 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 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…
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…