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/georgeturneruk/tckit/tc-docs-writenpx skills add georgeturneruk/tckit --skill tc-docs-writegit clone --depth 1 https://github.com/georgeturneruk/tckitWrote 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/georgeturneruk/tckit/tc-docs-write)<a href="https://agentmods.dev/skills/georgeturneruk/tckit/tc-docs-write"><img src="https://agentmods.dev/badge/skills/georgeturneruk/tckit/tc-docs-write.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 | $0.00172 | $0.01015 |
| Opus 5 | $0.00086 | $0.00508 |
| Sonnet 5 | $0.00034 | $0.00203 |
| Haiku 4.5 | $0.00017 | $0.00102 |
Grade A, and why
tc-docs-write 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 5d 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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Writing TcKit docs
The TcKit docs site lives under docs/content/ (MkDocs). The README at the repo root mirrors a slice of it. Both are user-facing surfaces and follow the same voice rules.
When to update docs
A change touches user-facing behaviour, and therefore needs a docs update in the same PR, if any of the following are true:
- MCP tool names, arguments, or return shapes changed
- CLI commands or flags changed
- Config keys changed (
config.json,~/.tckit/permissions.json,.env) - Install or setup steps changed
- Ports, adapters, or the one-rule architecture statement changed
- An ADR moved to
Implementedfor a design decision that has now shipped
If none of those apply, the change does not need a docs update. Don't invent one.
Which surface to update
- README — only when the surface shown on the README itself has changed. The README is a slice, not the whole story; many real-behaviour changes affect
docs/content/only. docs/content/— the default. Find the page that owns the changed surface (capability page for tool/argument changes, getting-started for install, architecture page for the one-rule statement, etc.) and edit there.
If the README and the relevant docs/content/ page both need to change, both go in the PR.
Voice rules
The home page (docs/content/index.md) takes its voice from the README. When editing the home page, match the README's structure, density, and tone. (The capability and adapter pages under docs/content/capabilities/ are denser reference material and have their own appropriate voice — don't apply this rule to them.)
For every user-facing page:
- No ADR references. ADRs are an internal design store.
docs/content/, the README, MCP tool descriptions, and CLI help text describe current behaviour, not the history of how it got there. If a passage needs more context than fits inline, link to the PR. Never link toadrs/. - No history paragraphs. Don't chronicle what something used to be. "The port had two more methods in an earlier draft" belongs on the ADR or in the commit message, not on a page describing the current shape.
- No marketing scaffolding on the home page. Specifically, do not add:
- problem/solution framing tables that repeat the capabilities list (e.g. "What TcKit solves")
- redundant capability summaries ("X at a glance" next to a capabilities table)
- "Design philosophy" or similar sections that duplicate the architecture page
- feature-pitch bullet lists
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.
- 5d ago First seen · 65 lines · 172 tokens per session scan A edb1048d3135
tc-docs-write is a skill published in the GitHub repository georgeturneruk/tckit (5 stars, last pushed 11d ago), licensed MIT. It adds 172 tokens to every session and 1,015 once invoked, about $0.0009 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 2026-08-31.
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…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…