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/stefanrossmeier/ai-craftkit/adrgennpx skills add stefanrossmeier/ai-craftkit --skill adrgengit clone --depth 1 https://github.com/stefanrossmeier/ai-craftkitWrote 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/stefanrossmeier/ai-craftkit/adrgen)<a href="https://agentmods.dev/skills/stefanrossmeier/ai-craftkit/adrgen"><img src="https://agentmods.dev/badge/skills/stefanrossmeier/ai-craftkit/adrgen.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 5.1 | $0.00000 | $0.11313 |
| Opus 5 | $0.00000 | $0.05657 |
| Sonnet 5 | $0.00000 | $0.02263 |
| Haiku 4.5 | $0.00000 | $0.01131 |
Grade A, and why
adrgen 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 — 2,041 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Adrgen Skill
Command: /adrgen
Generate evidence-based Architecture Decision Records and ADR-related decision documents for the currently opened repository.
The skill supports four modes:
/adrgen discover
/adrgen generate
/adrgen capture
/adrgen prepare
The skill inspects repository evidence when needed, uses the ADR template, removes unused or irrelevant template sections, and writes the final decision documentation to the repository’s docs/adr/ folder.
Purpose
/adrgen helps humans and agents document architectural decisions in a practical, traceable, and evidence-based way.
The goal is to create decision documentation that helps future humans and agents:
- understand why an architectural choice exists
- distinguish decisions from implementation details
- see which alternatives were considered
- understand consequences and trade-offs
- find evidence in code, docs, issues, discussions, pull requests, or human input
- avoid repeating old debates without new evidence
- avoid changing important architecture accidentally
- mark uncertainty instead of inventing rationale
- turn reviewed ADR candidates into useful ADR drafts
The goal is not to create generic ADR boilerplate.
Modes
adrgen has four first-class modes.
discover
generate
capture
prepare
Each mode has a different purpose, source basis, and output behavior.
Recommended lifecycle:
discover = find undocumented decisions in the repository
generate = turn reviewed candidates into ADR drafts
capture = record the result of a discussion
prepare = prepare alternatives before a discussion
Mode 1: Discover
Command:
/adrgen discover
Purpose:
Find architectural decisions that appear to exist in the repository but are not documented yet.
Use this mode when:
- the repository has architecture patterns but few or no ADRs
- the user wants to identify missing decision records
- the codebase contains important structural choices that future agents should understand
archdochas already documented the repository and now decisions should be extracted from it- the user wants a reviewable list of ADR candidates before generating ADR files
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 2,041 lines · 0 tokens per session scan A 6524da44390e
adrgen is a skill published in the GitHub repository stefanrossmeier/ai-craftkit (5 stars, last pushed 29d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 11,313 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 2026-08-31.
Other skills, from other repositories
documentation-patterns
Technical documentation patterns for READMEs, ADRs, API docs (OpenAPI 3.1), changelogs, and writing style guides. Use when creating project documentation, writing architecture decisions, documenting APIs, or maintaining changelogs.
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", "add AGENTS.md and a plan queue", or invokes /bootstrap.…
agent-wave
Orchestrate a wave of parallel agents over the plan/todo queue in a documentation-led repo — asks how many agents, the budget (items/waves, with hours as a soft cap), and whether to checkpoint after each wave or run continuously. Spawns isolated worktree subagents, assigns one queue item each, collects results. Use…
audit
Audit a documentation-led repo against its own conventions — contiguous ADR numbering, INDEX sync, plan/ coverage, required sections, status validity, cross-reference resolution, language mandate, ADR-privacy leaks into user-visible code, cross-worktree collisions (duplicate numbers, duplicate plan ownership, same ADR…
new-adr
Author a new ADR — record a DECISION (what the system must do, or how it is built) in a documentation-led repo. Picks the next contiguous number, chooses the shape (capability vs technology), fills the template, sets status Proposed, regenerates INDEX, updates domain READMEs, handles supersede/deprecate linkage…
add-convention
Assess and add a CONVENTION (a reusable rule, practice, or naming/process standard) to a documentation-led repo — decides FIRST whether it is worth codifying at all, then routes it to the right home (AGENTS.md hard rule, CONVENTIONS.md guidance, GLOSSARY term, or to /new-adr if it is really a one-off decision). Pushes…