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 rvdbreemen/adr-kit --skill initgit clone --depth 1 https://github.com/rvdbreemen/adr-kitWrote 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/rvdbreemen/adr-kit/init)<a href="https://agentmods.dev/skills/rvdbreemen/adr-kit/init"><img src="https://agentmods.dev/badge/skills/rvdbreemen/adr-kit/init/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/rvdbreemen/adr-kit/init"><img src="https://agentmods.dev/badge/skills/rvdbreemen/adr-kit/init.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 | $0.00027 | $0.00633 |
| Opus 5.5 | $0.00011 | $0.00253 |
| Sonnet 5.5 | $0.00005 | $0.00127 |
| Haiku 4.5 | $0.00003 | $0.00063 |
Grade A, and why
init 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 11d 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.
What it actually says
Initialize ADR Kit (the adopt mode of setup)
Reply in the language the user writes in; default to English. Keep command output, identifiers, paths, and ADR file content unchanged.
Invoke explicitly with $adr-kit:init when needed.
Resolve <plugin-root> from this installed skill, and <python> to the
first of python3, python or, on Windows, py -3 that runs Python 3.10
or newer. Use only bundled, local ADR Kit tools and follow this canonical
workflow:
- Run the setup workflow, preview legacy ADR migration, and audit the workspace.
- Create selected reconstruction candidates as Proposed and present them in small batches.
- Use a compact confirmation grill only when the chosen decision, rationale, alternatives, and consequences have direct cited evidence; otherwise use the full grill and confirm each ADR separately.
- Install the ADR Kit-owned pre-commit gate, then state plainly that the declarative gate is free and always on while the LLM pass is on by default and costs one model call per
llm_judge: trueADR on every commit touching its scope, linear in their number and nothing at all until an author opts one in. - Record the host backend with
adr-judge --set-backend host --host-client <this client's id>rather than by writing JSON (the host model is the only backend, ADR-036; operators can override per run with ADR_KIT_LLM_CMD), never prompt for or store an API key, and add docs/adr/.adr-kit.local.json to .gitignore. - Ask the user about the LLM layers, one at a time, showing each layer's current value from
<python> <plugin-root>/bin/adr-settings --adr-dir docs/adr: keep it on (the default and the recommendation) or turn it off for this machine. The layers are the per-commit judge pass (judge.llm_enabled; can block a commit; one model call per in-scopellm_judge: trueADR), the missing-decision nudge (suggest.enabled; never blocks) and the guardian's LLM tier (guardian.llm_enabled; asks before each run). All three run on this client's own model; no API key is involved. Apply each 'off' with<python> <plugin-root>/bin/adr-settings --adr-dir docs/adr --set <switch>=false --local, never change a value the user did not answer, and record the answer, also when everything stays on, with--set llm.confirmed=<YYYY-MM-DD> --local(ADR-049). - Finish with
adr-doctor --fix-index docs/adr/.
Do not contact another model or mutate user-owned instructions.
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.
- 11d ago Changed · +2 lines 792e277c2519
- 13d ago Changed · +3 lines 0a6de5ceeabe
- 1mo ago First seen · 22 lines · 27 tokens per session scan A 9a5ac794b7b9
init is a skill published in the GitHub repository rvdbreemen/adr-kit (13 stars, last pushed yesterday), licensed MIT. It adds 27 tokens to every session and 633 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
decision-backfill
Use when auditing an existing codebase, documentation set, plans, RFCs, or git history for architecture decisions that were made but never recorded as ADRs, and when triaging potential records before drafting them.
decision-memory
Use when planning, designing, reviewing, or changing code in a repository that keeps ADRs (usually docs/adr) — to load the decisions that already govern the work, check a plan or diff against them, or record a new decision. Also use when a choice feels already-settled and you cannot find where it was settled.
bootstrap
Scaffold or retrofit documentation-led conventions (AGENTS.md, CLAUDE.md, CONVENTIONS.md, ADR catalogue, plan/ queue, agent/ coordination) into a repo. Use when the user asks to "set up conventions", "bootstrap ADRs", "scaffold the documentation-led layout", or "add AGENTS.md and a plan queue". Works on fresh repos…
agent-wave
Run a bounded wave over the plan/todo queue in a documentation-led repo, using available parallel agents or sequential execution. Establishes width, budget and supervision; isolates work and collects verified outcomes. Use for "spawn a wave of agents", "run the queue in parallel", "fan out the work", or "agent wave"…
new-plan
Queue a UNIT OF WORK in the plan/todo queue of a documentation-led repo, tracing to an existing ADR — names the owning ADR(s), scope, exit criteria mapped to acceptance criteria, dependencies, and queue position. Use when the user says "add a plan item", "queue this work", "create a todo for ADR X", "new plan", "put…
actual
Feature-complete companion for the actual CLI, an ADR-powered CLAUDE.md/AGENTS.md generator. Runs and troubleshoots actual adr-bot, status, auth, config, runners, and models, plus the Actual AI platform surface: login, logout, whoami, and advisor (org-scoped architecture Q&A). Covers all 5 runners (claude-cli…