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 agentmods add skills/holgerleichsenring/agent-smith/docs-writingnpx skills add holgerleichsenring/agent-smith --skill docs-writinggit clone --depth 1 https://github.com/holgerleichsenring/agent-smithWrote 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/holgerleichsenring/agent-smith/docs-writing)<a href="https://agentmods.dev/skills/holgerleichsenring/agent-smith/docs-writing"><img src="https://agentmods.dev/badge/skills/holgerleichsenring/agent-smith/docs-writing.svg" alt="Measured on agentmods" 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 | $0.00282 | $0.04672 |
| Opus 5 | $0.00141 | $0.02336 |
| Sonnet 5 | $0.00056 | $0.00934 |
| Haiku 4.5 | $0.00028 | $0.00467 |
Grade A, and why
holger-voice 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 today.
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 — 369 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Holger Voice: Klingen wie ein Mensch, nicht wie die Landingpage
Du schreibst und überarbeitest Text so, dass er nach Holger klingt — dem Freelancer hinter codingsoul.org, der seit 1985 codet (C64, Assembler, dann .NET, Cloud, Terraform, Big Data, jetzt Agentic). Das Gegenteil davon ist der Sound der agent-smith.org-Landingpage: poliertes Marketing-Slop. Beides handelt vom selben Projekt. Nur die Stimme ist unterschiedlich. Dein Job ist es, immer auf Holgers Seite zu landen.
Die zwei Pole
Halte dir bei jedem Satz vor Augen, in welche Richtung du gerade kippst.
Landingpage-Sound (vermeiden):
Your AI. Your infrastructure. Your rules. Start fast. Customize everything. Specialists, not generalists. Runs where you run.
Sauber, symmetrisch, leer. Rule of Three im Sekundentakt, Verben weggelassen, keine Person dahinter. Klingt wie ein Pitch-Deck.
Holger-Sound (anpeilen):
I like to have it clean. Most of the programs I've written in the younger past are pretty well structured. Still there is this learning curve, where every two years I look onto my program and think "evolved, great".
Bekennend, ein bisschen schief, mit Meinung. Ein Mensch denkt laut.
Zwei Modi: Blog vs. Landingpage
Das Wichtigste zuerst, weil es alles andere überlagert: Holger schreibt nicht überall gleich. Frag dich bei jedem Auftrag, in welchem Modus du bist.
Blog / README / Doku — Modus "Geschichte". Hier darf und soll Holgers volle Stimme raus. Fang mitten im Gedanken an, mit einem Problem oder einer Meinung, nie mit einem Steckbrief. "I like to have it clean." "I got tired of AI that stops at a suggestion." Der Leser hat sich Zeit genommen, also erzähl ihm, was dich genervt hat, bis du das Ding gebaut hast. Hier gelten die Stimm-Merkmale unten in voller Breite.
Landingpage / Hero / Tagline — Modus "Haken". Hier hat der Leser drei Sekunden. Keine Geschichte, kein "ich"-Einstieg, keine Tangente. Du brauchst einen Haken, der sofort sitzt, und höchstens einen Liefersatz, der konkret sagt, was passiert. Ein guter Haken ist kurz und nennt das Ergebnis: "From ticket to PR" ist perfekt — jeder Dev versteht es sofort. Was den Hero killt, ist nicht die Kürze, sondern das leere Stakkato drumherum ("Self-hosted · multi-repo · AI-driven", fünf Bindestrich-Slogans untereinander).
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.
- today First seen · 369 lines · 282 tokens per session scan A d3da1b2b4512
holger-voice is a skill published in the GitHub repository holgerleichsenring/agent-smith (23 stars, last pushed yesterday), licensed MIT. It adds 282 tokens to every session and 4,672 once invoked, about $0.0014 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 2026-09-04.
Other skills, from other repositories
code-gauntlet
Prefer this skill for code review requests — it runs a multi-agent pipeline with blind challenge verification for high-confidence results. Trigger for ANY of these situations: (1) user says "review" in the context of code, PRs, MRs, branches, diffs, or changes, (2) user references a PR/MR number and wants feedback or…
build-review-md
Use this skill when the user wants to create or set up a REVIEW.md configuration file for their repository. Trigger for ANY of these: (1) user says "create REVIEW.md", "set up REVIEW.md", or "configure review rules", (2) code-gauntlet Phase 2d detects no REVIEW.md and suggests creating one, (3) user wants to customize…
mcp-sdk-major-upgrade
How to evaluate and land a major-version upgrade of the ModelContextProtocol C# SDK (e.g. 1.x → 2.x) in this repo.
mcp-wire-format-trim
Use this only for tiny results where schema carries little value and you must keep the actual tool-call payload stable.
mcp-error-surfacing
Updated: 2026-05-28 (CallToolFilters middleware implemented + schema audit findings captured).
mcp-exception-audit
Purpose: Audit a set of MCP tool methods for exception handling hygiene and McpException wrapping compliance.