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/loncadev/baron/claude-mdgit clone --depth 1 https://github.com/loncadev/baronWrote 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/loncadev/baron/claude-md)<a href="https://agentmods.dev/instructions/loncadev/baron/claude-md"><img src="https://agentmods.dev/badge/instructions/loncadev/baron/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 | $0.01063 | $0.01063 |
| Opus 5 | $0.00531 | $0.00531 |
| Sonnet 5 | $0.00213 | $0.00213 |
| Haiku 4.5 | $0.00106 | $0.00106 |
Grade A, and why
baron 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 4d 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Baron — Project Rules
Baron is a platform-agnostic work-orchestration layer for AI coding agents. It lets an agent (or a CI pipeline) drive work tracking, source control, and notifications across many providers through one normalized contract, instead of hardwiring a single vendor's API and one team's process template into prompts.
Read ARCHITECTURE.md first — it is the single source of truth for the foundational decisions. This file is the day-to-day working contract.
Tech stack
- TypeScript (NodeNext, strict), ESM only. Node >= 20.
- pnpm workspaces monorepo.
- vitest (tests), biome (lint + format), tsup (build for publish).
Local development
pnpm install
pnpm test # vitest run (all packages)
pnpm typecheck # tsc --noEmit per package
pnpm lint # biome check
pnpm lint:fix # biome check --write
Workspace packages resolve to source (src/index.ts) in dev — no build step needed to run
tests or typecheck. publishConfig in each package.json flips main/types/exports to dist
for release; pnpm build (tsup) produces it. Do not point dev consumers at dist.
Architecture invariants (do not violate without revisiting ARCHITECTURE.md)
- Capability ports, not "a tracker." Work is organized into independent ports —
issues,scm,notify,docs— each bound to a provider independently. A consumer mixes providers (Linear issues + GitHub PRs + Slack notify). Never assume one provider spans all ports. - Semantic role layer. Recipes and primitives speak abstract roles
(
backlog → ready → in_progress → in_review → done, plusblocked). Providers map their native states/columns/labels onto roles via config (baron initintrospects + a human confirms). Never hardcode a provider-native state in core or recipe logic. - Primitives in core, workflows in recipes. The core exposes primitives only
(
issue.create,issue.transition, ...). Workflow opinion (when to move toin_review, PR body shape, hierarchy rules) lives in declarative YAML recipes outside the core. Do not bake workflow opinion into the core or into an adapter. - Adapters carry no translation logic. An adapter contributes only a
CapabilityManifestand anIssuesTransport(provider I/O). All role↔native translation and gap negotiation live in the sharedBaseIssuesAdapter. If you find yourself writing role/state mapping inside an adapter, it belongs in core. - Capability gaps are never silent. When an operation needs a capability the provider lacks,
behavior is decided by explicit policy:
error(loud, actionable),emulate:<strategy>(synthesize, e.g. GitHub hierarchy via labels), ordegrade(skip +warnlog). A gap that is neither errored nor logged is a bug.
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.
- 4d ago First seen · 80 lines · 1,063 tokens per session scan A b6b219c9a874
baron CLAUDE.md is an instructions file published in the GitHub repository loncadev/baron (1 stars, last pushed 13d ago), licensed Apache-2.0. It adds 1,063 tokens to every session, about $0.0053 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
agent-smith CLAUDE.md
Claude Code instructions for holgerleichsenring/agent-smith, covering agent-smith — ai agent instructions, context files (read in this order), phase directory structure, experiential memory (remember / recall) and minting a phase id.
teamxray copilot-instructions.md
Copilot instructions for AndreaGriffiths11/teamxray, covering github copilot instructions for mcp team x-ray extension, response style, build, test, and lint commands, validating extension changes and architecture.
teamxray AGENTS.md
AGENTS.md instructions for AndreaGriffiths11/teamxray, covering agents.md, purpose, tagline, tech stack and architecture.
github-mcp-server copilot-instructions.md
Copilot instructions for github/github-mcp-server, covering github mcp server - copilot instructions, project overview, critical build & validation steps, required commands (run before committing) and when modifying mcp tools/endpoints.
av CLAUDE.md
Claude Code instructions for aviator-co/av, covering claude.md, project overview, documentation sources, command structure philosophy and development workflow.
vscode-gitlens CLAUDE.md
Claude Code instructions for gitkraken/vscode-gitlens, a project described as: Supercharge Git inside VS Code and unlock untapped knowledge within each repository — Visualize code authorship at a glance via Git blame annotations and CodeLens, seamlessly navigate and explore Git repositories, gain valuable insights via…