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/fabioconcina/claumon/claude-mdgit clone --depth 1 https://github.com/fabioconcina/claumonWrote 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/fabioconcina/claumon/claude-md)<a href="https://agentmods.dev/instructions/fabioconcina/claumon/claude-md"><img src="https://agentmods.dev/badge/instructions/fabioconcina/claumon/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 | $0.00678 | $0.00678 |
| Opus 5 | $0.00339 | $0.00339 |
| Sonnet 5 | $0.00136 | $0.00136 |
| Haiku 4.5 | $0.00068 | $0.00068 |
Grade A, and why
claumon 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 6d 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 — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
claumon
Real-time Claude Code dashboard — single binary, zero config. Monitors API usage, token costs, sessions, and memory files via a local web UI on port 3131.
Build & Test
make build # builds ./claumon with version from git tags
make build-benchtools # build including the dev-only bench/diagnostics subcommands
make test # go test -v -race -count=1 ./...
make vet # go vet ./...
./claumon --open # run and open browser
The bench and diagnostics subcommands (forecast model benchmarking and
calibration replay) are gated behind the benchtools build tag, so they are
excluded from release binaries. Use make build-benchtools (or
go build -tags benchtools .) to enable them locally.
Architecture
Single main.go orchestrates 4 goroutines (SSE broker, usage API poller, file watcher, pricing refresh) and an HTTP server. All packages live under internal/:
- api — Claude OAuth usage API client with exponential backoff
- auth — Multi-platform credential loading (macOS Keychain, Linux secret-service, Windows Credential Manager)
- parser — Session JSONL discovery and token/cost aggregation
- pricing — Layered pricing: embedded JSON → 24h cache → GitHub remote → config overrides
- memory — Memory file discovery, graph building, staleness detection, consolidation scoring
- server — HTTP routes, handlers, SSE broker
- store — SQLite (WAL mode) for usage snapshots and daily aggregates
- watcher — fsnotify-based file watcher with 500ms debounce
Frontend is a single web/index.html embedded via //go:embed. No build step, no external JS deps.
extension/ is a separate VS Code extension (TypeScript): a thin client that reads the same /api/usage + SSE feed and renders usage/forecast in the status bar plus an embedded dashboard panel. It has its own Node toolchain, version, and lockfile, and zero runtime dependencies (compiled with tsc, not bundled). It is not part of the Go build and is published separately (see the ext-v* tag in .github/workflows/publish-extension.yml).
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.
- 6d ago First seen · 45 lines · 678 tokens per session scan A f244ab2c1fde
claumon CLAUDE.md is an instructions file published in the GitHub repository fabioconcina/claumon (16 stars, last pushed 1mo ago), licensed MIT. It adds 678 tokens to every session, about $0.0034 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
Vibe-Research AGENTS.md
AGENTS.md instructions for simonlin1212/Vibe-Research, covering vibe-research-agent 金融研究宪法, 0. 三条不可越线, 1. 数据纪律(五问 gate:给出任何数字或结论前逐条自问), 2. 研究哲学(评估框架,不是预测工具) and 3. 估值口径(你只选输入、解释输出;计算交给 calc/).
worldmonitor AGENTS.md
AGENTS.md instructions for koala73/worldmonitor, covering agents.md, task mode and authority, start here, surface routing and architecture invariants.
vizro copilot-instructions.md
Copilot instructions for mckinsey/vizro, covering github copilot instructions for vizro, pull requests from bots and automated tooling and everything else.
openclaw-dashboard CLAUDE.md
Claude Code instructions for mudrii/openclaw-dashboard, covering go development standards, project constraints, internal packages, environment and commands.
metabase copilot-instructions.md
Copilot instructions for metabase/metabase, covering metabase developer assistant instructions, code review standards, security critical issues, performance red flags and code quality essentials.
neko-master copilot-instructions.md
Instructions for foru17/neko-master: All repo guidance lives in AGENTS.md — commands, code conventions, key contracts, and the project map. Follow it.