aichronicles CLAUDE.md

A set of project rules for developing aichronicles in Go, including commit style, code conventions, and tests.

In plain words
What is it for?
Use it when adding features, fixing bugs, writing tests, or preparing commits in the aichronicles Go project.
Why use it?
It gives contributors consistent expectations for making changes and helps keep each change small, reviewable, and passing the project's checks.

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/toabctl/aichronicles/claude-md
Clone the repo
git clone --depth 1 https://github.com/toabctl/aichronicles
Per session 876 This file is loaded in full into every session.
When invoked 876 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 $0.00876 $0.00876
Opus 5 $0.00438 $0.00438
Sonnet 5 $0.00175 $0.00175
Haiku 4.5 $0.00088 $0.00088

Measured 2d ago against content hash fa7ac36d6b16, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

aichronicles 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 · 53 lines

How it starts

The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.

aichronicles — development practices

These rules are load-bearing. Follow them for every change.

1. Conventional commit messages

Use type(scope): summary — e.g. feat(ingest): add /v1/ingest handler, fix(store): handle nil session_id, docs(openapi): document redaction behavior.

Allowed types: feat, fix, docs, refactor, test, chore, perf, build, ci, revert. Subject line ≤ 72 chars, imperative mood, no trailing period.

2. Small commits, one logical change

Each commit does exactly one thing and leaves the tree green (go build, go test, lints all pass). Split mechanical changes (renames, moves) from behavior changes. If a commit message needs "and", it should probably be two commits.

3. Idiomatic Go, current language features

Target the toolchain in go.mod. Prefer stdlib first. Specifically:

  • log/slog for structured logging (no third-party loggers)
  • errors.Is / errors.As / %w wrapping (no string matching)
  • context.Context as the first argument of anything that can block, I/O, or be cancelled
  • net/http with Go 1.22+ ServeMux patterns (no web framework by default)
  • Generics only where they remove real duplication, never for fashion
  • any over interface{}
  • No init() for business logic

Run gofmt, go vet, staticcheck (or golangci-lint) before every commit.

4. Unit tests for every feature

Every new function or behavior ships with tests in the same package (_test.go). Prefer table-driven tests. Use t.Run for subtests, t.Parallel() where safe, testing.T.Helper() in helpers. No external test deps unless there's a clear reason.

A PR without tests for new logic is not ready.

5. Integration tests

Cover the seams that unit tests can't: real SQLite, the UDS listener, the ingest CLI end-to-end. Live under ./integration/... with a build tag (//go:build integration) so go test ./... stays fast and go test -tags=integration ./... runs the full suite. CI runs both.

6. Never guess — always root-cause

Read the full file on GitHub · 53 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 · 53 lines · 876 tokens per session scan A fa7ac36d6b16

Subscribe to this mod's changes

aichronicles CLAUDE.md is an instructions file published in the GitHub repository toabctl/aichronicles (2 stars, last pushed 7d ago), licensed Apache-2.0. It adds 876 tokens to every session, about $0.0044 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.

Related

Other instructions, from other repositories