What is aigon CLAUDE.md?

A project-specific instruction file for Claude Code, the command-line coding assistant. It points to the main agent instructions and explains which detailed documents to read before changing different parts of the Aigon codebase.

Use it to guide coding-agent work in the Aigon repository, especially changes involving specifications, templates, the dashboard, lifecycle state, or tests.

It helps Claude Code follow Aigon’s safety rules, file ownership rules, and development workflow instead of making changes in the wrong place.

How jayvee/aigon configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to jayvee/aigon. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/jayvee/aigon/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/jayvee/aigon

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/jayvee/aigon/claude-md.svg)](https://agentmods.dev/instructions/jayvee/aigon/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/jayvee/aigon/claude-md"><img src="https://agentmods.dev/badge/instructions/jayvee/aigon/claude-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 2,161 This file is loaded in full into every session.

When invoked 2,161 The same file — it is already loaded in full.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

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	$0.02161	$0.02161
Opus 5	$0.01081	$0.01081
Sonnet 5	$0.00432	$0.00432
Haiku 4.5	$0.00216	$0.00216

Measured 2d ago against content hash e35371b7f176, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

aigon 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.

CLAUDE.md · 42 lines

How it starts

The opening of the file, as written. The whole thing — 42 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Aigon — CLAUDE Pointer

The always-loaded orientation lives in AGENTS.md — read that first for the load-bearing safety invariants (public-repo hygiene, target-repo zero-opinion, template source-of-truth, lifecycle authority, ctx pattern, dashboard gallery, server-restart, test/commit discipline) and reading pointers. Deep reference — repo structure, the module map, state architecture, install internals — lives on-demand in docs/architecture.md (and testing detail in docs/testing.md); read those when the task touches their area.

Hot rules (read before editing)

F313 frontmatter: feature/research specs carry complexity: YAML only; model/effort defaults resolve at start from templates/agents/<id>.json cli.complexityDefaults then config (not from the spec). Parser: lib/cli-parse.js parseFrontMatter. Resolver: lib/spec-recommendation.js. Dashboard reads via /api/recommendation/:type/:id and pre-selects the start-modal dropdowns.

Run args verbatim — never add agents/flags from context.
Slash commands: templates/generic/commands/ — never edit .claude/commands/ copies. Cursor always-on rule: templates/generic/cursor-rule.mdc → install to .cursor/rules/aigon.mdc via aigon install-agent cu; do not edit the installed file as source (re-install overwrites).
After any lib/*.js edit, run aigon server restart.
After any templates/dashboard/index.html edit, take an MCP browser_snapshot (a11y tree) — fall back to browser_take_screenshot only when the change is purely visual (CSS, layout, color). See CONTRIBUTING.md § Browser MCP. All screenshots must be saved to ./tmp/ — never write PNG/JPG files to the repo root. When verifying dashboard UI from a worktree, run aigon preview <feature-id> and snapshot that preview URL (<agent>-<id>.aigon.localhost) — never the primary aigon.localhost (main checkout HTML) and never aigon server start from the worktree (that collides with the primary dashboard). Automated regression = tests/dashboard-e2e/bootstrap.js / npm run test:browser; interactive UI verification = aigon preview <id>.
Never move spec files manually — use aigon CLI commands for state transitions. 5b. Dashboard frontend (dash-arch F620–F628): templates/dashboard/js/ is ES modules (entry js/main.js); data enters only via store.js replaceData (optimism = overlays, never hand-mutation); views register in js/view-registry.js; CSS sheets live in templates/dashboard/styles/ and must be listed in styles/manifest.json (served concatenated at /styles.css); no CDN scripts — vendor under js/vendor/. New /api/status fields that should repaint cards must be added to computeStatusFingerprint (lib/dashboard-status-version.js) or the ETag/SSE pipeline won't push them. Full contract: docs/architecture.md § Dashboard Frontend.

Read the full file on GitHub · 42 lines

Changes

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 · 42 lines · 2,161 tokens per session scan A e35371b7f176

Subscribe to this mod's changes

aigon CLAUDE.md is an instructions file published in the GitHub repository jayvee/aigon (25 stars, last pushed 5d ago), licensed Apache-2.0. It adds 2,161 tokens to every session, about $0.0108 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 2026-09-03.

Building agents Planning agent-orchestration ai-agents claude-code cli codex developer-tools

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

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.

openai/codex · 5,182 tokens

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).

microsoft/vscode · 6,785 tokens

aigon: Instructions file for Claude Code