codealmanac CLAUDE.md

A repository guide for AI coding agents working on codealmanac, a living wiki that records important codebase knowledge in linked Markdown pages. It defines how features should fit the existing Python architecture and which sources of information to trust.

In plain words
What is it for?
Use it when implementing features, mapping a Python codebase, recording design decisions, or checking flows, rules, incidents, and known problems in the repository.
Why use it?
It helps prevent features from being added to an unsuitable code structure and keeps agents aligned with the project’s maintained architectural notes.

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/almanaccode/codealmanac/claude-md
Clone the repo
git clone --depth 1 https://github.com/AlmanacCode/codealmanac
Per session 3,544 This file is loaded in full into every session.
When invoked 3,544 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 $0.03544 $0.03544
Opus 5 $0.01772 $0.01772
Sonnet 5 $0.00709 $0.00709
Haiku 4.5 $0.00354 $0.00354

Measured 2d ago against content hash 03be3536706f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

codealmanac 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 · 164 lines

How it starts

The opening of the file, as written. The whole thing — 164 lines — stays where its author put it; the contents beside it link to each section on GitHub.

COMPULSORY — read MANUAL.md before implementing any feature. It defines how we build: living architecture (the unit of work is "reshape the codebase so the feature fits, then build it"), the seam-vs-machinery rule, the duty to stop and flag when the current shape won't hold a feature cleanly, and the wireframe-in-chat habit. Reason from it; don't bolt features onto a misshapen base.

codealmanac is a living wiki for codebases, maintained by AI coding agents. It documents what the code can't say — decisions, flows, invariants, incidents, gotchas — as atomic, interlinked markdown pages living in the repo-local almanac/ tree. New Python repos use almanac/ only. There is no docs/almanac/, .almanac/, custom-root, or old CLI compatibility path. Primary consumer is the AI coding agent; humans benefit secondarily.

Trust order: current code > Almanac > ordinary repository documentation.

When code and the Almanac disagree, trust the code. When the Almanac and ordinary documentation disagree, trust the Almanac. Do not prefer ordinary docs over the Almanac; the Almanac is maintained more regularly and is more authoritative.

Historical spec: /Users/rohan/Desktop/Projects/openalmanac/docs/ideas/codebase-wiki.md — useful background, not current product truth where it conflicts with notes.md and implementation-tickets.md. Read it before making design changes, then apply the current reset decisions in this repo.

Python rewrite architecture references

The active rewrite is a local-only Python codebase. Before non-trivial Python implementation, read docs/python-port-live-agreement.md and the relevant local Architecture Patterns with Python chapters under docs/reference/cosmic-python/.

Use the book as architecture reference, not as a package template. The main transfer is: services own product verbs, stores own persistence, ports live near the service that owns the contract, integrations implement those ports, and src/codealmanac/app.py is the composition root.

Useful chapter map:

  • Persistence/store boundaries: chapter_02_repository.md
  • CLI/API-to-service boundary: chapter_04_service_layer.md
  • Service-level tests: chapter_05_high_gear_low_gear.md
  • Transaction boundaries: chapter_06_uow.md
  • Command/request objects: chapter_10_commands.md
  • Composition root/dependency wiring: chapter_13_dependency_injection.md

When a Cosmic Python idea justifies a design choice, quote the relevant line briefly in the plan or response and cite the local chapter path. Keep the generated Markdown reference files as book text; CodeAlmanac notes belong in docs/reference/cosmic-python/CODEALMANAC.md, repo docs, or wiki pages.

Read the full file on GitHub · 164 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 · 164 lines · 3,544 tokens per session scan A 03be3536706f

Subscribe to this mod's changes

codealmanac CLAUDE.md is an instructions file published in the GitHub repository AlmanacCode/codealmanac (990 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 3,544 tokens to every session, about $0.0177 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 2026-08-30.