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/aenix-io/aeman/claude-mdgit clone --depth 1 https://github.com/aenix-io/aemanWrote 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/aenix-io/aeman/claude-md)<a href="https://agentmods.dev/instructions/aenix-io/aeman/claude-md"><img src="https://agentmods.dev/badge/instructions/aenix-io/aeman/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 | $0.01929 | $0.01929 |
| Opus 5 | $0.00964 | $0.00964 |
| Sonnet 5 | $0.00386 | $0.00386 |
| Haiku 4.5 | $0.00193 | $0.00193 |
Grade A, and why
aeman 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 today.
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 — 58 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.
What this is
aeman — a short-term planning system for engineering teams. Git repositories are the only storage — a board is one or more repositories (domains) of YAML/Markdown files, every action a commit; the whole thing ships as one self-contained Go binary: an embedded React SPA (go:embed via web/embed.go), a JSON REST API under /api/v1, a WebSocket watch stream, and an MCP server for AI agents — all driving the same board service, with the repositories as the single source of truth. GitHub (or another forge) is only the identity provider and the remote the repositories live on.
Commands
make build # SPA (npm ci + vite build) then the single Go binary
make backend # Go binary only (expects web/dist to exist)
make frontend # SPA once into web/dist
make run # go run ./cmd/aeman serve (frontend must be built once)
make lint # golangci-lint run (CI pins golangci-lint v2, .golangci.yaml)
make fmt # golangci-lint fmt
make test # go test ./...
- Single Go test:
go test ./pkg/board -run TestMeView(any package/regexp). - Frontend (from
web/):npm run typecheck,npm test(vitest), single test file:npx vitest run src/theme.test.ts. - CI (
.github/workflows/ci.yml) runs golangci-lint, the frontend build + vitest,make backend, andgo test ./...— all of it must pass locally before pushing.
Architecture
The server holds an in-memory cache of the board (internal/server/boardstore.go) over shallow clones of the board's repositories under --data; every write path (UI, REST, MCP) goes through one board service, is answered from the cache at once, and lands as one commit per request (gitstore.WithScope) that a background sync pushes; a fetch tick brings other replicas' commits in, a rejected push is re-applied by replaying the unpushed commits field by field (gitstore.Repo.Rebase). A change reloads only the touched cards and fans out to every open board via the watch stream, filtered by what each visitor may read. Design: docs/design/git-backend.md; rules G1–G26 in docs/design/behavior-matrix.md.
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.
- today Changed · +1 lines · +242 tokens per session 79376f9cacf9
- 5d ago First seen · 57 lines · 1,687 tokens per session scan A fd419cbcfa08
aeman CLAUDE.md is an instructions file published in the GitHub repository aenix-io/aeman (31 stars, last pushed yesterday), licensed Apache-2.0. It adds 1,929 tokens to every session, about $0.0096 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
orbit CLAUDE.md
Instructions for Noveum/orbit, covering orbit, hard rules, bun is the toolchain, not the runtime, layout and commands.
orbit AGENTS.md
Instructions for Noveum/orbit, covering agent instructions, the short version, rules that will fail the build and before you report a task finished.
AgentVibes CLAUDE.md
Claude Code instructions for paulpreibisch/AgentVibes, covering agentvibes — development guidelines, what this is, repo map, architecture invariants (hard-won — do not regress) and non-destructive configuration rule (mandatory).
Epoch copilot-instructions.md
Copilot instructions for KyaniteLabs/Epoch, covering coding-agent adapter and empower the orchestrator.
Epoch CLAUDE.md
Claude Code instructions for KyaniteLabs/Epoch, covering claude adapter and empower the orchestrator.
agile_v_skills AGENTS.md
AGENTS.md instructions for Agile-V/agile_v_skills, covering agents.md — agile v skills library, repository context, project overview, repository structure and build / lint / test commands.