agentmods.dev

leansdd: Skill for Claude Code

.agents/skills/leansdd-audit/SKILL.md

leansdd-audit is a skill for Claude Code, Codex from kidpixo/leansdd. It costs 30 tokens per session (372 once invoked), scanned A, original, MIT.

A report-only check for the health of a Lean SDD project. Lean SDD is a way to keep software decisions, plans, constraints, and structure documented alongside the code.

In plain words
What is it for?
Use it for periodic maintenance reports on a Lean SDD project and to give a human a list of findings and suggested actions.
Why use it?
It finds stale proposals, missing paths, roadmap drift, outdated maps, and constraints that may no longer match the code without changing files.

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 30 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-audit/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-audit

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/kidpixo/leansdd/leansdd-audit"><img src="https://agentmods.dev/badge/skills/kidpixo/leansdd/leansdd-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 30 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 372 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 $0.00030 $0.00372
Opus 5.5 $0.00012 $0.00149
Sonnet 5.5 $0.00006 $0.00074
Haiku 4.5 $0.00003 $0.00037

Measured 5d ago against content hash 0eb9d2e93882, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

leansdd-audit 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-audit/SKILL.md · 30 lines

What it actually says

Lean SDD audit (hygiene report)

A periodic, report-only pass. This skill never edits .ai/ files — it produces a findings list for the human, who decides what to act on.

  1. Run the consistency check and include its output verbatim: python .ai/scripts/leansdd-check.py
  2. Rotting proposals: list Proposed ADRs with their age (the script warns after 14 days; list all of them here with dates).
  3. Ghost scopes: for each Active ADR, check whether the paths in its Scope still exist (glob relative to the .ai/ parent). Report scopes matching nothing.
  4. Roadmap drift: compare 02_ROADMAP.md In-scope items against 03_CURRENT_STATUS.md — items done but still in scope, or in NOW but absent from the roadmap.
  5. Dead constraints: for each hard rule in 00_CONSTRAINTS.md, grep the codebase for evidence it is still relevant; report constraints with no plausible referent (best effort — say so, do not judge).
  6. Map health (if enabled): commits since the 01_STRUCTURE.md stamp, and whether SYMBOLS.txt is older than HEAD.
  7. Present everything as a table: finding, severity (high/med/low), suggested owner action. End with: "no files were modified."

Stale Proposed ADRs are the usual top finding: propose activating, rejecting, or superseding each one explicitly.

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 · 30 lines · 30 tokens per session scan A 0eb9d2e93882

Subscribe to this mod's changes

leansdd-audit is a skill published in the GitHub repository kidpixo/leansdd (2 stars, last pushed 6d ago), licensed MIT. It adds 30 tokens to every session and 372 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 2026-11-01.

LLMPlanningWriting and docssdd
Related

leansdd-audit compared with skills from other repositories

leansdd-audit next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
leansdd-auditkidpixo/leansddSkill26d agoMITA30Claude Code, Codex
speckit-constitutionsarveshtalele/mcp-skills-registrySkill31mo agoMITA46Claude Code, Codex
speckit-plansarveshtalele/mcp-skills-registrySkill31mo agoMITA51Claude Code, Codex
speckit-specifysarveshtalele/mcp-skills-registrySkill31mo agoMITA58Claude Code, Codex
speckit-taskssarveshtalele/mcp-skills-registrySkill31mo agoMITA52Claude Code, Codex
subagent-driven-developmentNousResearch/hermes-agentSkill261kyesterdayMITA17Claude Code, Codex
mcporterNousResearch/hermes-agentSkill261kyesterdayMITA16Claude Code, Codex