Borrowing it
Nothing to install: this file belongs to gotgenes/pi-anthropic-auth. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/gotgenes/pi-anthropic-auth/main/.pi/skills/markdown-conventions/SKILL.mdgit clone --depth 1 https://github.com/gotgenes/pi-anthropic-authWrote 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/gotgenes/pi-anthropic-auth/markdown-conventions)<a href="https://agentmods.dev/skills/gotgenes/pi-anthropic-auth/markdown-conventions"><img src="https://agentmods.dev/badge/skills/gotgenes/pi-anthropic-auth/markdown-conventions/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/gotgenes/pi-anthropic-auth/markdown-conventions"><img src="https://agentmods.dev/badge/skills/gotgenes/pi-anthropic-auth/markdown-conventions.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 | $0.00043 | $0.02164 |
| Opus 5.5 | $0.00017 | $0.00866 |
| Sonnet 5.5 | $0.00009 | $0.00433 |
| Haiku 4.5 | $0.00004 | $0.00216 |
Grade A, and why
markdown-conventions 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 — 155 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Markdown Conventions
Load this skill when writing or editing markdown files.
Formatting rules
The enforcer is rumdl (runs as part of pnpm run lint, available standalone via pnpm run lint:md; also the pre-commit rumdl fmt hook), not markdownlint-cli2 — there is no markdownlint binary in this repo.
lint:md covers *.md docs/**/*.md only, so it skips .pi/**; check a skill, prompt, or agent with pnpm exec rumdl check .pi.
Checking a file outside the repository (a scratch sample in /tmp) needs --config .rumdl.toml — rumdl does not discover repo config for it, so MD013 fires against the default 80-character limit.
Rules below are named by their markdownlint MDxxx IDs because rumdl implements the same rule family; use the IDs for reference, not the tool.
Lines and sentences
- Use one sentence per line (unbroken) for better diffs. Each sentence occupies exactly one line; never wrap a sentence across lines or place two sentences on the same line. This applies to all prose, including list-item continuations.
rumdl'sMD057can report an existing relative link as missing when its sentence runs long; split the sentence per the rule above rather than hunting the path.- Author and append markdown with the
Write/Edittools, not shell heredocs (cat <<EOF) — heredocs don't interpolate\uXXXXescapes and make one-sentence-per-line slips easy, both of which trip the markdown linter.
Non-ASCII in authored prose
An em-dash in a newText/content body is unreliably emitted, in four forms: a literal \u2014, a bare newline that splits the sentence, a newline plus u2014, or an invisible \x0c form feed plus literal text (erence2 for an em-dash, erence6 for an ellipsis).
All four are valid markdown that rumdl accepts, and no gate in this repo catches any of them.
The corruption is upstream of every tool: measured in pi-packages across 1764 session transcripts, 62 of 122 form-feed occurrences sat in plain assistant prose with no tool call involved, so Edit writes faithfully what the model already emitted.
After writing prose, re-read the region and scan it:
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 Changed · +69 lines · -6 tokens per session 50b69f547d6d
- 1mo ago Changed · +9 lines c688ba9fc808
- 2mo ago First seen · 77 lines · 49 tokens per session scan A 0b5f45614521
markdown-conventions is a skill published in the GitHub repository gotgenes/pi-anthropic-auth (426 stars, last pushed 13d ago), licensed MIT. It adds 43 tokens to every session and 2,164 once invoked, about $0.0002 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
prose-review
Review prose written for others (e.g., user-facing documentation, prompts for other LLMs, reports, plans, inline comments, docstrings) for local jargon leakage, orphaned references, missing grounding, and audience or genre mismatch. Always run on prose you produce or materially edit, except for routine conversational…
text-search
Search indexed text corpora with qmd. For indexed content, prefer qmd over grep.
rp
Always read this skill when the user mentions "rp" or "repoprompt", or before accessing a repository outside the current RepoPrompt workspace. Covers workspace discovery, binding, root verification, and workspace hygiene.
auth-patterns
Use when implementing authentication (JWT, sessions, OAuth), authorization (RBAC, ABAC), password hashing, MFA, or security best practices for backend services.
pi-tui-design
Create distinctive, crafted TUI components for pi using @mariozechner/pi-tui and @mariozechner/pi-coding-agent. Use when building interactive terminal UIs — custom components, overlays, dialogs, dashboards, widgets, data visualizations, animated elements, game-like interfaces, or any visual TUI work inside pi…
auth0-docs
Auth0 — identity platform: auth flows, Universal Login, SSO, identity providers, MFA, RBAC, Actions, tokens.