agentmods.dev

leansdd: Skill for Claude Code

.agents/skills/leansdd-adr-mine/SKILL.md

leansdd-adr-mine is a skill for Claude Code, Codex from kidpixo/leansdd. It costs 40 tokens per session (359 once invoked), scanned A, original, MIT.

A tool for finding possible architecture decisions in a mature codebase by examining a limited amount of Git history and project comments. An ADR, or architecture decision record, documents a technical decision and how to verify it.

In plain words
What is it for?
Use it to draft candidate ADRs for an existing project by reviewing commits, reversals, tags, and decision-like comments.
Why use it?
It separates evidence from guesses and requires human confirmation before any proposed decision becomes an official record.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is kidpixo/leansdd's own configuration. It tells Claude Code and Codex how to work on leansdd 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 leansdd configures →

not rated 2repo 6d ago A scan 40 tokens original MIT
View source ↗ kidpixo/leansdd kidpixo.github.io
Reuse

Borrowing it

Nothing to install: this file belongs to kidpixo/leansdd. 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/kidpixo/leansdd/master/.agents/skills/leansdd-adr-mine/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/kidpixo/leansdd

Made for: Claude Code, Codex.

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 leansdd-adr-mine

README.md
[![agentmods](https://agentmods.dev/badge/skills/kidpixo/leansdd/leansdd-adr-mine/github.svg)](https://agentmods.dev/skills/kidpixo/leansdd/leansdd-adr-mine)
Your own site
<a href="https://agentmods.dev/skills/kidpixo/leansdd/leansdd-adr-mine"><img src="https://agentmods.dev/badge/skills/kidpixo/leansdd/leansdd-adr-mine/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 leansdd-adr-mine

Your own site · 80×15
<a href="https://agentmods.dev/skills/kidpixo/leansdd/leansdd-adr-mine"><img src="https://agentmods.dev/badge/skills/kidpixo/leansdd/leansdd-adr-mine.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 40 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 359 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 $0.00040 $0.00359
Opus 5.5 $0.00016 $0.00144
Sonnet 5.5 $0.00008 $0.00072
Haiku 4.5 $0.00004 $0.00036

Measured 5d ago against content hash b43003048bcb, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

leansdd-adr-mine 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.

.agents/skills/leansdd-adr-mine/SKILL.md · 35 lines

What it actually says

Lean SDD ADR mining (brownfield, opt-in)

Reconstructs candidate decisions from an existing repo's history. Highest hallucination risk in the framework: commits suggest decisions, they do not prove them. Everything produced here is Proposed, and nothing becomes Active without a human writing or approving the Verification.

Mine

  1. Bounded scan only:
    • git log --oneline -100 (never the full history)
    • merge commits and commits touching >30% of the tree (git log --merges -20)
    • git tag and milestones
    • TODO/FIXME/HACK comments in the top two directory levels
  2. Look for decision-shaped patterns: "switch X to Y", "remove Z", "never do W" (reverted commits and their re-revert), repeated guard-rail fixes.
  3. For each candidate, gather evidence: commit hashes, before/after file paths. No evidence, no candidate.

Propose

For each candidate, present to the human:

  • one-line decision statement, and the evidence for it
  • whether the decision still holds today (check the current code)
  • a draft Verification check that could prove it

Only after the human confirms a candidate, create the ADR via the leansdd-adr skill, with the human's confirmed statement — not the mined guess — as the Decision. Mark anything unconfirmed (inferred — confirm).

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. 5d ago First seen · 35 lines · 40 tokens per session scan A b43003048bcb

Subscribe to this mod's changes

leansdd-adr-mine is a skill published in the GitHub repository kidpixo/leansdd (2 stars, last pushed 6d ago), licensed MIT. It adds 40 tokens to every session and 359 once invoked, about $0.0002 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 2026-11-01.

Git and workflowLLMPlanningsdd
Related

leansdd-adr-mine compared with skills from other repositories

leansdd-adr-mine next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
leansdd-adr-minekidpixo/leansddSkill26d agoMITA40Claude Code, Codex
deployment-patternsaffaan-m/ECCSkill298k4d agoMITA41Claude Code, Kiro
mem0-test-integrationmem0ai/mem0Skill68k2d agoApache-2.0A207Claude Code, Codex
resolve-handoffomnigent-ai/omnigentSkill11kyesterdayApache-2.0A23Claude Code, Codex
otto-pr-review-loopomnigent-ai/omnigentSkill11kyesterdayApache-2.0A17Claude Code, Codex
baby-sitlangchain-ai/open-sweSkill11kyesterdayMITA30Claude Code, Codex
merge-drivelangwatch/langwatchSkill5.0kyesterdayApache-2.0A154Claude Code