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/bullboy1/babycoding/agents-mdgit clone --depth 1 https://github.com/bullboy1/babycodingWhat 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 | $0.02533 | $0.02533 |
| Opus 5 | $0.01267 | $0.01267 |
| Sonnet 5 | $0.00507 | $0.00507 |
| Haiku 4.5 | $0.00253 | $0.00253 |
Grade A, and why
babycoding AGENTS.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.
This is a copy
98% identical to babycoding copilot-instructions.md — 2 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md — Function Registry Protocol (FRP) v1.4
Mandatory for every task in this repo. Goals: zero duplicate code, minimal token spend, clean layered architecture.
0. Session start
- Read
FUNCTIONS.md. If Stage 3 (sharded): read root index + only the shards of modules this task touches. - No
FUNCTIONS.md→ run §6 Bootstrap before anything else. - Function count crossed a §7 threshold → perform that stage upgrade within this task.
- Canvas on → read
docs/registry/inbox.mdif present; pending entries are user requests sent from the canvas: do them first, mark each[done YYYY-MM-DD]when finished.
1. Lookup — before writing ANY function
- Search
FUNCTIONS.md(name + desc columns) by capability keywords. - HIT → grep the code to confirm existence and signature → REUSE. Reimplementing a registered capability is a protocol violation.
- NEAR-HIT (covers ≥80% of the need) → EXTEND the existing function (add a param/option). Do not create a sibling.
- MISS → create, following §2–§4.
- Mandatory trace — print one line per decision in your reply, before writing code:
REGISTRY: HIT parseDate (L1) src/utils/time.pyREGISTRY: EXTEND fetchOrder (L3) src/orders/api.py — add includeDrafts flagREGISTRY: MISS -> new renderBadge (L2) src/ui/badge.tsx
2. Creation rules
- Names: verb+noun, repo's dominant casing (
parseInvoice/parse_invoice). Searchable; no abbreviations except: id, url, db, cfg, ctx. - One function, one responsibility. Function ≤ 50 lines. File ≤ 300 lines. Nesting ≤ 3 levels.
- Rule of Three: a 2nd duplication is tolerated; the 3rd MUST be extracted into a shared L1/L2 component and registered.
- Folders: depth ≤ 4 from repo root, lowercase, named by domain/feature — never by person, date, or version.
- Imports flow downward only: L4 → L3 → L2 → L1. L1 imports no project code. An upward import is a bug.
- Shared constants/types obey the same lookup-before-create rule (grep first).
- Comments explain WHY, never WHAT. One-line docstring required on L1/L2; on L3/L4 only when non-obvious.
- Minimal diff: touch nothing outside task scope. No drive-by refactors.
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 · 105 lines · 2,533 tokens per session scan A a899158f44fe
babycoding AGENTS.md is an instructions file published in the GitHub repository bullboy1/babycoding (4 stars, last pushed 1mo ago), licensed MIT. It adds 2,533 tokens to every session, about $0.0127 per session on Opus 5. A static security scan graded it A with 0 findings. It is 98% identical to babycoding copilot-instructions.md, differing in 2 lines, and is treated as a copy.
Other instructions, from other repositories
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).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
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.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.