Borrowing it
Nothing to install: this file belongs to georgeturneruk/tckit. 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/georgeturneruk/tckit/main/.claude/skills/tc-adr/SKILL.mdgit 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-adr)<a href="https://agentmods.dev/skills/georgeturneruk/tckit/tc-adr"><img src="https://agentmods.dev/badge/skills/georgeturneruk/tckit/tc-adr/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/georgeturneruk/tckit/tc-adr"><img src="https://agentmods.dev/badge/skills/georgeturneruk/tckit/tc-adr.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 | $0.00269 | $0.02337 |
| Opus 5 | $0.00134 | $0.01169 |
| Sonnet 5 | $0.00054 | $0.00467 |
| Haiku 4.5 | $0.00027 | $0.00234 |
Grade A, and why
tc-adr 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 10d 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 — 190 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Working with TcKit ADRs and findings
ADRs live under adrs/ as one Markdown file per decision; the template is at
adrs/0000-template.md. Findings live under
bench/findings/ as date-prefixed records of bench rounds and
post-implementation reviews. Both surfaces share an always-fresh index file
and a layered reading discipline.
Reading order (this is the centrepiece)
Always go top-down:
- Index first.
adrs/README.mdandbench/findings/README.md. One-line summaries with status. Cheap to load; cheaper than scanning frontmatter of every file. - Current state block of any ADR that intersects the task. After frontmatter, before Context. Up to about six lines. This block is canonical: it captures the live decision in its post-implementation form, including any deviations.
- Body (Context / Decision / Alternatives / Consequences) only when you need rationale or the original framing.
- Status notes for the change journal, if you need the trail.
If Current state and the Decision section disagree on a question, Current state wins. The Decision section may be a snapshot of how the design was originally proposed; deviations flow back into Current state, not into Decision.
Status lifecycle
Frontmatter status is one of:
Exploring: investigation is in flight; no specific proposal yet. Use this for "here are the options we've evaluated and what we know about each".Proposed: a recommended direction has crystallised and is awaiting review.Accepted: the design has been agreed; implementation may not have started.Implemented: the PR has landed. Fill inpr:with the GitHub PR number.Superseded: abandoned or replaced. Add a Status notes entry explaining why. Setsuperseded_by:(and where applicable, the replacement'ssupersedes:). Do not delete the file.
Promote forwards by editing the status field, rewriting Current state to
match the new reality, and adding a dated entry to Status notes. Never
skip a step silently; if you go straight from Exploring to Implemented,
the trail is missing.
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.
- 10d ago First seen · 190 lines · 269 tokens per session scan A 2ad1429d6725
tc-adr is a skill published in the GitHub repository georgeturneruk/tckit (5 stars, last pushed 16d ago), licensed MIT. It adds 269 tokens to every session and 2,337 once invoked, about $0.0013 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…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…