agentmods.dev

tckit: Skill for Claude Code

.claude/skills/tc-adr/SKILL.md

tc-adr is a skill for Claude Code from georgeturneruk/tckit. It costs 269 tokens per session (2,337 once invoked), scanned A, original, MIT.

A workflow for Architecture Decision Records, which are written records of important software design choices, and for documenting benchmark findings.

In plain words
What is it for?
Use it to read, write, update, or approve ADRs in adrs/, and to add findings under bench/findings/.
Why use it?
It keeps decisions and findings organized by status and directs you to the current decision before older background details.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions CLAUDE.md.

This is georgeturneruk/tckit's own configuration. It tells Claude Code how to work on tckit itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything tckit configures →

not rated 11repo +1 2mo ago A scan 269 tokens original MIT
View source ↗ georgeturneruk/tckit tckit.org
Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/georgeturneruk/tckit/main/.claude/skills/tc-adr/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/georgeturneruk/tckit

Made for: Claude Code.

Wrote 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.

agentmods badge for tc-adr

README.md
[![agentmods](https://agentmods.dev/badge/skills/georgeturneruk/tckit/tc-adr/github.svg)](https://agentmods.dev/skills/georgeturneruk/tckit/tc-adr)
Your own site
<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.

agentmods 80×15 button for tc-adr

Your own site · 80×15
<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>
Per session 269 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,337 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00269 $0.02337
Opus 5.5 $0.00108 $0.00935
Sonnet 5.5 $0.00054 $0.00467
Haiku 4.5 $0.00027 $0.00234

Measured 2mo ago against content hash 2ad1429d6725, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

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 2mo 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.

.claude/skills/tc-adr/SKILL.md · 190 lines

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:

  1. Index first. adrs/README.md and bench/findings/README.md. One-line summaries with status. Cheap to load; cheaper than scanning frontmatter of every file.
  2. 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.
  3. Body (Context / Decision / Alternatives / Consequences) only when you need rationale or the original framing.
  4. 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 in pr: with the GitHub PR number.
  • Superseded: abandoned or replaced. Add a Status notes entry explaining why. Set superseded_by: (and where applicable, the replacement's supersedes:). 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.

Read the full file on GitHub · 190 lines

Changes

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.

  1. 2mo ago First seen · 190 lines · 269 tokens per session scan A 2ad1429d6725

Subscribe to this mod's changes

tc-adr is a skill published in the GitHub repository georgeturneruk/tckit (11 stars, last pushed 2mo ago), licensed MIT. It adds 269 tokens to every session and 2,337 once invoked, about $0.0011 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.

PlanningWriting and docs
Related

tc-adr compared with skills from other repositories

tc-adr next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
tc-adrgeorgeturneruk/tckitSkill112mo agoMITA269Claude Code
imagegenopenai/codexSkill134ktodayApache-2.0A113Codex
local-ai-agentsmicrosoft/ai-agents-for-beginnersSkill79ktodayMITA200Claude Code, Codex
playwright-climicrosoft/playwrightSkill99ktodayApache-2.0A19Claude Code
systematic-debuggingobra/superpowersSkill314k3d agoMITA21Claude Code
next-cache-components-adoptionvercel/next.jsSkill143ktodayMITA95Claude Code
chat-pet-sprite-creationmicrosoft/vscodeSkill195ktodayMITA53Claude Code, Codex