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/reyamira/aic/claude-mdgit clone --depth 1 https://github.com/reyamira/aicWrote 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.
[](https://agentmods.dev/instructions/reyamira/aic/claude-md)<a href="https://agentmods.dev/instructions/reyamira/aic/claude-md"><img src="https://agentmods.dev/badge/instructions/reyamira/aic/claude-md.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00907 | $0.00907 |
| Opus 5 | $0.00453 | $0.00453 |
| Sonnet 5 | $0.00181 | $0.00181 |
| Haiku 4.5 | $0.00091 | $0.00091 |
Grade A, and why
aic 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 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.
How it starts
The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Build & Development
mise run build # Build binary → ./aic
mise run test # Run all tests (go test ./...)
mise run run <args> # Run without building (go run . <args>)
Releases are handled by GoReleaser via GitHub Actions on version tags (v*). The main.version variable is set at build time via -X main.version={{.Version}} ldflags.
To release: git tag v<X.Y.Z> && git push origin v<X.Y.Z>
Architecture
Go CLI built with Cobra for command/flag handling, using the Charm ecosystem (lipgloss, bubbletea, glamour) for terminal UI. Fetches changelogs for AI coding assistants from the GitHub Releases API.
File Structure
| File | Purpose |
|---|---|
main.go |
Cobra command definitions, flag registration, createSourceCommand() |
sources.go |
Source type, sources map, config (load/save/XDG), enabledSources() |
fetch.go |
ChangelogEntry/Section types, fetchGitHubReleases(), parseReleaseBody() |
output.go |
Output formatters: outputJSON(), outputMarkdown(), outputPlainText(), outputRendered() (glamour), outputVersionList() (lipgloss table) |
status.go |
runStatusCommand() — lipgloss table with concurrent fetch + install detection |
latest.go |
runLatestCommand() — concurrent fetch, 24h filter |
config.go |
runConfigCommand() — bubbletea interactive source picker |
pick.go |
runPickCommand() — bubbletea interactive version picker |
helpers.go |
formatRelativeTime(), calculateAvgReleaseFreq(), openBrowser(), truncateString() |
Key Libraries
- Cobra — command routing, flag parsing with short/long aliases, mutual exclusivity, grouped help
- Lipgloss (
lipgloss/table) — styled tables instatus.goandoutput.go - Glamour — markdown rendering for changelogs in
output.go. Auto-detects TTY; falls back to plain text when piped. - Bubbletea — interactive TUI for config picker (
config.go) and version picker (pick.go)
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.
- 5d ago First seen · 65 lines · 907 tokens per session scan A cc3392ffd2c3
aic CLAUDE.md is an instructions file published in the GitHub repository reyamira/aic (26 stars, last pushed 3mo ago), licensed MIT. It adds 907 tokens to every session, about $0.0045 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.
Other instructions, from other repositories
portfolio_rs AGENTS.md
AGENTS.md instructions for MarkusZoppelt/portfolio_rs, covering agents.md, verify (matches ci, .github/workflows/rust.yml) and gotchas.
awesome-cli-apps AGENTS.md
AGENTS.md instructions for agarrharr/awesome-cli-apps, a project described as: 🖥 📊 🕹 🛠 A curated list of command line apps.
renux AGENTS.md
AGENTS.md instructions for andrianllmm/renux, covering agents.md, layout, testing and tags registry is the source of truth.
laravel-release-changelog-generator AGENTS.md
AGENTS.md instructions for lightszentip/laravel-release-changelog-generator, covering agents.md, commands, architecture, core workflow and key components.
harmonyhub-py AGENTS.md
Instructions for jenreh/harmonyhub-py, covering harmonyhub-py, 1) golden rules, 2) task bootstrap pattern, 3) tooling decision matrix and 4) sop — development workflow.
chlog CLAUDE.md
Instructions for luizjhonata/chlog, covering claude.md, what this project does, build & development commands, architecture and key external libraries.