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/christopher-buss/bedrock/technical-writernpx skills add christopher-buss/bedrock --skill technical-writergit clone --depth 1 https://github.com/christopher-buss/bedrockWrote 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/christopher-buss/bedrock/technical-writer)<a href="https://agentmods.dev/skills/christopher-buss/bedrock/technical-writer"><img src="https://agentmods.dev/badge/skills/christopher-buss/bedrock/technical-writer.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 | $0.00000 | $0.01381 |
| Opus 5 | $0.00000 | $0.00691 |
| Sonnet 5 | $0.00000 | $0.00276 |
| Haiku 4.5 | $0.00000 | $0.00138 |
Grade A, and why
technical-writer 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 4d 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 — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Technical writing craft rules
Apply these rules when producing or editing developer documentation prose. Follows the spirit of the Google Developer Documentation Style Guide without being tied to any one brand guide. Complements the Diátaxis framework: Diátaxis tells you which quadrant (tutorial, how-to, reference, explanation) a page belongs to; these rules tell you how to write each sentence once the quadrant is fixed.
When to apply
Trigger when the user is:
- Writing a new docs page (tutorial, how-to, reference entry, explanation, getting-started, README, migration guide).
- Reviewing or revising an existing docs page for quality.
- Diagnosing why a docs page feels flat, bloated, or confusing.
Skip for: commit messages, PR descriptions, ADRs, internal design docs, code comments. Those have their own registers.
Structure rules
- Open with a one-sentence summary. The first line must tell the reader what they will learn or accomplish. If removing the opening sentence leaves the page's purpose unclear, it was doing work.
- H2 sections as scannable signposts. Each heading is a promise: the reader should know what they'll get from the section without reading it. Prefer verb-led headings for task pages, noun phrases for reference.
- Order by frequency, not logic. Most common use case first, edge cases last. A reader who stops reading halfway should still have hit the 80% path.
- Inverted pyramid within each section. Lead with the most important sentence. Supporting detail follows. Caveats and edge cases end the section.
- One topic per H2. If a section covers two things, split it. Skim readers rely on the heading matching the content.
Voice and register
- Active voice, present tense. "Bedrock reads the config" beats "The config is read by bedrock." Passive is acceptable only when the agent genuinely doesn't matter.
- Second person for instructions ("you configure"), third person for concepts ("bedrock configures"). Do not mix within a section.
- Sentence case headings. Proper nouns keep their capitals.
- Concrete over abstract. Name the file, the function, the command. "Run
pnpm build" beats "build the project." - No filler openers. Cut "In order to", "It is important to note that", "Please note that", "Basically".
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.
- 4d ago First seen · 90 lines · 0 tokens per session scan A 5c4ed5126775
technical-writer is a skill published in the GitHub repository christopher-buss/bedrock (14 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,381 tokens. 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 2026-09-01.
Other skills, from other repositories
Cloud Security & Container Hardening
AWS/Azure/GCP security auditing, container and Kubernetes hardening, Infrastructure as Code scanning, and cloud compliance assessment.
pulumi-component
Guide for authoring Pulumi ComponentResource classes. Use when creating reusable infrastructure components, designing component interfaces, setting up multi-language support, or distributing component packages.
pulumi-migrate-from-discovered-stack
Migrate a CloudFormation or ARM stack into a Pulumi stack, sourced from a stack that Pulumi Cloud's Discovery feature has already found and exposed via the discovered-stacks API. Load this skill when the user has a discovered stack in Pulumi Cloud and wants to bring its resources under Pulumi management. Do NOT load…
pulumi-overview
Use this skill for any task that creates, modifies, inspects, or destroys cloud infrastructure or SaaS configuration, from one-off CLI operations to full multi-resource projects, across providers in the Pulumi ecosystem. A typical project spans many providers (AWS or Azure or GCP, Kubernetes, Cloudflare, Auth0…
provider-upgrade
Upgrade any Pulumi provider to a newer version and reconcile the resulting diff. Use when users want to upgrade or update a provider (including editing package.json, requirements.txt, pyproject.toml, go.mod, or Pulumi.yaml to bump a provider SDK), check for breaking changes before or during an upgrade, fix resources…
pulumi-best-practices
Load when the user is writing, reviewing, or debugging Pulumi TypeScript/Python programs; asks about Output or apply() usage; wants to create ComponentResource classes; needs to refactor resources without destroying them (aliases); is setting up secrets or config; or is configuring a pulumi preview/up CI workflow.…