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 fmind/dotfiles --skill technical-publishinggit clone --depth 1 https://github.com/fmind/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/fmind/dotfiles/technical-publishing)<a href="https://agentmods.dev/skills/fmind/dotfiles/technical-publishing"><img src="https://agentmods.dev/badge/skills/fmind/dotfiles/technical-publishing/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/fmind/dotfiles/technical-publishing"><img src="https://agentmods.dev/badge/skills/fmind/dotfiles/technical-publishing.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00029 | $0.00514 |
| Opus 5.5 | $0.00012 | $0.00206 |
| Sonnet 5.5 | $0.00006 | $0.00103 |
| Haiku 4.5 | $0.00003 | $0.00051 |
Grade A, and why
technical-publishing 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 — 30 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Publish Technical Articles
Carry one article from an evidence-backed source draft to its canonical public form without losing authorship, links, metadata, or proof boundaries. Use hugo for site mechanics and typst for standalone reports.
Workflow
- Resolve the source of truth: Identify the canonical repository, article identifier, target audience, publication surfaces, and existing public URL before editing. Preserve unrelated drafts and generated artifacts.
- Define the claim: Write the reader's problem, the article's useful conclusion, and the evidence needed to support it. Remove claims that cannot be verified or clearly label them as opinion or inference.
- Research current sources: Prefer installed source, standards, primary documentation, and reproducible experiments. Record dates and versions for facts likely to drift; paraphrase within source and copyright limits.
- Draft for one reading path: Lead with the outcome, keep code minimal and runnable, explain trade-offs at the decision point, and provide safe failure and recovery guidance.
- Validate the artifact: Run formatting, links, code examples, site build, metadata, images, accessibility, canonical URL, and the repository's full gate. Inspect the rendered page, not only Markdown.
- Prepare each surface: Derive exports from the canonical source, adapt only platform-specific metadata and length, and verify that links still point back to the canonical article.
- Publish only with authority: Treat commits, pushes, deploys, cross-posts, newsletters, and social messages as distinct external mutations. Never infer them from a request to edit or review.
- Verify publicly: After publication, fetch the public page and confirm title, body, code, images, canonical metadata, links, and deployment revision. Keep local, deployed, indexed, and analytics evidence separate.
Handoff
Report the canonical source and URL, supported claims, validation performed, exact surfaces changed, and any manual publication, indexing, or analytics check that remains.
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 · 30 lines · 29 tokens per session scan A 4c88ae76bd9c
technical-publishing is a skill published in the GitHub repository fmind/dotfiles (4 stars, last pushed 1mo ago), licensed MIT. It adds 29 tokens to every session and 514 once invoked, about $0.0001 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 2026-08-31.
Other skills, from other repositories
full-review
Full review: read every repo area, apply verified fixes, and prove all checks pass.
duckdb
Query and export CSV, Parquet, JSON, or SQLite data with DuckDB.
observability
Instrument Python services and agents: structlog logs, OpenTelemetry traces and metrics.
resolve-conflicts
Resolve Git merge or rebase conflicts by both sides' intent; verify the result.
skill-security-review
Review third-party skills and agent extensions for supply-chain risk.
sops-secrets
Encrypt, rotate, and inject Git secrets with sops and age.