A project-documentation setup process that surveys a code repository and creates or refreshes a concise CONTEXT.md file. The file records facts that future coding agents might otherwise get wrong.

Use it to document languages, frameworks, workspace or monorepo layout, tests, linters, setup steps, environment variables, and important architectural decisions.

It saves agents from repeatedly rediscovering build commands, project structure, required settings, and unusual coding rules. It also avoids silently replacing existing project guidance.

init — Skill by initxy

Install

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.

agentmods

npx agentmods add skills/initxy/noeta/init

Any agent

npx skills add initxy/noeta --skill init

Clone the repo

git clone --depth 1 https://github.com/initxy/noeta

Made for: Claude Code, Codex.

Per session 18 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 445 The whole file, excluding the scripts and references it only reads on demand.

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	$0.00018	$0.00445
Opus 5	$0.00009	$0.00222
Sonnet 5	$0.00004	$0.00089
Haiku 4.5	$0.00002	$0.00044

Measured 2d ago against content hash 4ee677aa98f2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

init 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.

tests/_skills_builtin/init/SKILL.md · 39 lines

What it actually says

Init project docs

Generate or refresh the repository's CONTEXT.md so future agents can be productive fast. Keep it concise — only include what an agent would get wrong without it.

Follow any extra instructions the user gave in the conversation.

Steps

Survey the project. Use read on the manifests you find with grep/shell_run: pyproject.toml, package.json, Cargo.toml, go.mod, README.md, Makefile, CI config, any existing CONTEXT.md, CLAUDE.md, AGENTS.md, .cursor/rules, docs/adr/. Run shell_run for git status context if useful.
Detect and record only the non-obvious facts:
- Build / test / lint commands that an agent cannot guess (custom scripts, flags, how to run a single test).
- Languages, frameworks, package manager, monorepo / workspace layout.
- Code-style rules that differ from language defaults.
- Required env vars, setup steps, gotchas, key architectural decisions.
Read any existing CONTEXT.md first. Do NOT silently overwrite it — propose concrete diffs and explain why each change helps. For a fresh file, write a minimal one with write_file; for an existing file, use replace_text / apply_patch for targeted edits.
Exclude: file-by-file structure (discoverable by reading code), standard language conventions, generic advice ("write clean code"), and long references — link those with a path instead of inlining.

Every line must pass the test: "Would removing this make an agent make mistakes?" If not, cut it. Do not invent sections like "Tips for Development" — only write facts you actually found in files you read.

(fork agent: general-purpose)

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 · 39 lines · 18 tokens per session scan A 4ee677aa98f2

Subscribe to this mod's changes

init is a skill published in the GitHub repository initxy/noeta (9 stars, last pushed 4d ago), licensed Apache-2.0. It adds 18 tokens to every session and 445 once invoked, about $0.0001 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.

Data and AI Documents LLM Testing agent ai-agents claude-code durable-execution event-sourcing

init

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

What it actually says

Init project docs

Steps

What this file has done since we first saw it

Other skills, from other repositories

aatmf-t10-confidentiality-breach

publish-registry

mochi-remind

memory

lazarus-group

sidewinder-rattlesnake