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.
npx agentmods add instructions/toabctl/aichronicles/claude-mdgit clone --depth 1 https://github.com/toabctl/aichroniclesWhat 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.
| Model | Per session | Once 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 |
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.
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/slogfor structured logging (no third-party loggers)errors.Is/errors.As/%wwrapping (no string matching)context.Contextas the first argument of anything that can block, I/O, or be cancellednet/httpwith Go 1.22+ServeMuxpatterns (no web framework by default)- Generics only where they remove real duplication, never for fashion
anyoverinterface{}- 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
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.
- 2d ago First seen · 53 lines · 876 tokens per session scan A fa7ac36d6b16
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.
Other instructions, from other repositories
dsh-rewind AGENTS.md
Instructions for SiriLee/dsh-rewind, covering agents.md, positioning & principles, common commands, layout at a glance and conventions.
terminal-title CLAUDE.md
Instructions for 2389-research/terminal-title, covering terminal title plugin, skills included, terminal-title, environment variables and title format.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.