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/jonnyton/tinyassets/agents-mdgit clone --depth 1 https://github.com/Jonnyton/TinyAssetsWhat 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 | $0.04124 | $0.04124 |
| Opus 5 | $0.02062 | $0.02062 |
| Sonnet 5 | $0.00825 | $0.00825 |
| Haiku 4.5 | $0.00412 | $0.00412 |
Grade A, and why
TinyAssets 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 yesterday.
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 — 281 lines — stays where its author put it; the contents beside it link to each section on GitHub.
TinyAssets
A goal-agnostic daemon engine. Bind it to a domain and let it run. The platform supports any multi-step AI workflow — research papers, screenplays, recipe trackers, novels, news summaries, any substantive long-running work.
Forever Rule: 24/7 uptime, zero hosts online
One unified priority, not a ranked list. Every surface works with no host online -- chatbot users through the live connector, daemon hosts installing the tray in under 5 minutes, contributors cloning and running cleanly, plus discovery, remix, converge, the paid-market inbox, and moderation.
Work ordering: take the task unblocking the largest currently-broken uptime surface, and treat every outage as equal severity -- tiering is what starves the quiet surfaces. Break ties by shared dependency impact, then shortest path to verified recovery. Everything else continues but never blocks uptime.
Architecture: docs/design-notes/2026-04-18-full-platform-architecture.md.
Two Living Files
AGENTS.md (here) is how to work: behaviour, norms, hard rules. PLAN.md is how the system works and why: architecture, principles, design. Architecture never goes here; norms never go there. Both update immediately when durable state changes.
Live state has no living file. It has homes by kind:
| Kind | Home |
|---|---|
| Queued / in-flight work | openspec/changes/ -- python scripts/openspec_flow.py audit |
| Unresolved findings | docs/concerns/ -- one file each, deleted when resolved |
| Founder-only work | docs/host-actions.md |
| Who is working on what | git branches and open PRs |
| Narrative / landings | .agents/activity.log / the git log |
Do not recreate
STATUS.md(retired 2026-08-25: 5.2x over its own declared ceiling, touched by 46% of its last 90 days of commits). One always-loaded file absorbing every kind of live state is the failure mode, not the format.
How to Work
Orient
PLAN.mdis the design reference. Full load for feature planning or design decisions;python scripts/docview.py headings PLAN.mdthen one section for scoped work; skip for routine test/doc edits.python scripts/openspec_flow.py auditis the work queue. Skimdocs/concerns/README.mdwhen the area has known-unresolved findings.- An approach conflicting with a
PLAN.mdprinciple does not get implemented -- file it indocs/concerns/. PLAN.md changes need user approval. - Before a design note proposing a new MCP action, citing an unfixed
BUG-NNN, or pinning a sha:python scripts/check_primitive_exists.py(exit 2 = collision).
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.
- yesterday First seen · 281 lines · 4,124 tokens per session scan A bf6deaf9c3ba
TinyAssets AGENTS.md is an instructions file published in the GitHub repository Jonnyton/TinyAssets (1 stars, last pushed yesterday), licensed MIT. It adds 4,124 tokens to every session, about $0.0206 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
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.
buildNext
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).
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.
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).
spec-kit 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.
langchain 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.