code-decisions CLAUDE.md

Repository instructions for a decision memory system that stores the reasons behind technical choices in shared Markdown files.

In plain words
What is it for?
They guide writing and searching decision records, maintaining their metadata and search index, and running the project's formatting, type, shell, and test checks.
Why use it?
They help future coding sessions understand past decisions instead of reopening the same design debates.

Instructions file

Install

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.

agentmods
npx agentmods add instructions/zimalabs/code-decisions/claude-md
Clone the repo
git clone --depth 1 https://github.com/zimalabs/code-decisions
Per session 1,229 This file is loaded in full into every session.
When invoked 1,229 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.01229 $0.01229
Opus 5 $0.00615 $0.00615
Sonnet 5 $0.00246 $0.00246
Haiku 4.5 $0.00123 $0.00123

Measured 2d ago against content hash a4fbba6d149c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

code-decisions CLAUDE.md 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 2d 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.md · 91 lines

How it starts

The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

What This Is

Decision memory for Claude Code — captures why choices were made so future sessions inherit context instead of repeating debates. Decisions are markdown files in .claude/decisions/ (committed to the repo, shared via git). Hooks and skills handle everything automatically.

Commands

uv sync                        # install dev deps (first time only)
make check                     # ruff + mypy + shellcheck + pytest
make dev                       # symlink plugin into Claude Code cache

Key Concepts

  • Decisions extend Claude Code's memory schema with: name, description, date, tags, affects
  • YAML frontmatter with --- delimiters (not TOML) for decision files. Block scalars (|, >) are rejected.
  • All decisions are lightweight — frontmatter, title, and lead paragraph. No weight distinction.
  • DecisionStore = file-based store with FTS5 derived search index. Progressive loading: index stores summaries, full files read on demand.
  • Zero-config, advise-only. No strictness settings, no config file. The plugin just nudges — it never blocks or enforces.

Storage

Decisions live at .claude/decisions/{slug}.md in the repo — committed to git and shared with the team. The FTS5 index lives at ~/.claude/projects/{project-key}/.decisions/.

Architecture Rules

Architecture lives in decision files under .claude/decisions/ — see .claude/rules/decisions.md for the full index.

  1. Markdown is source of truth. SQLite FTS5 is a derived index. Delete it and everything rebuilds.
  2. Git is the history layer. Edit decisions in place, delete when obsolete. Git tracks the evolution.
  3. Skill = intent + behavior, hooks = correctness, CLI = data access. /decision skill routes intent. Hooks enforce validation and inject context. CLI provides search, stats, and git operations.
  4. Pure methods on DecisionStore. No side effects at import time.
  5. Plugin is stdlib only. Zero external dependencies in src/.
  6. No confirmation prompts on capture. Write decisions directly — agents must capture without human approval gates. /decision undo is the safety net.

Read the full file on GitHub · 91 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. 2d ago First seen · 91 lines · 1,229 tokens per session scan A a4fbba6d149c

Subscribe to this mod's changes

code-decisions CLAUDE.md is an instructions file published in the GitHub repository zimalabs/code-decisions (5 stars, last pushed 1mo ago), licensed MIT. It adds 1,229 tokens to every session, about $0.0061 per session on Opus 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.