Borrowing it
Nothing to install: this file belongs to Jonnyton/TinyAssets. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Jonnyton/TinyAssets/main/CLAUDE.mdgit clone --depth 1 https://github.com/Jonnyton/TinyAssetsWrote 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/jonnyton/tinyassets/claude-md)<a href="https://agentmods.dev/instructions/jonnyton/tinyassets/claude-md"><img src="https://agentmods.dev/badge/instructions/jonnyton/tinyassets/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/jonnyton/tinyassets/claude-md"><img src="https://agentmods.dev/badge/instructions/jonnyton/tinyassets/claude-md.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00506 | $0.00506 |
| Opus 5.5 | $0.00202 | $0.00202 |
| Sonnet 5.5 | $0.00101 | $0.00101 |
| Haiku 4.5 | $0.00051 | $0.00051 |
Grade A, and why
TinyAssets 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 2mo 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 — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
@AGENTS.md
Claude Code
AGENTS.md is how to work here. This file is only harness quirks.
Merging and deploying
Background-job sessions cannot merge or push to main — that restriction is
injected into that session type and cannot be lifted from inside one. Check which
session type you are in before claiming you cannot merge; an interactive session
repeating "this session cannot merge" is misapplying the rule. Interactive
sessions merge normally; gh pr merge --auto works from either.
Green checks are not sufficient — inspect diff scope. PR #1491 presented as a
two-file auth fix and carried seven workflow files plus deploy-prod.yml and a
Dockerfile, because the branch sat on an unmerged 217-commit lineage. CI passed
on the parts it looked at. pr-scope-guard now catches this class; do not merge
around it.
Cross-family dispatch
Codex CLI is a second model family already in the harness, not something only a
human can start. Dispatch it as a background subprocess on its own budget via
the peer-agents skill — never wrap it in a Claude teammate to relay, which
burns a Claude context to do nothing.
Dispatch by default, not on request: before a review verdict, before a risky change, before a "done" claim on non-trivial work, and whenever stuck 3+ iterations. Ask it to refute, and log the verdict. A dispatched review gates landing, not your forward progress — take the next lane while it runs.
Session start
Read AGENTS.md (imported above) and let the sync gate report whether the
checkout is behind. There is no startup ritual beyond that.
Memory and skills
Per-agent memory lives in .claude/agent-memory/<name>/ — the named owner
writes, everyone reads. Skills are in .claude/skills/ (mirrored from the
canonical .agents/skills/); seven of them, named for their task, no router.
Verification
AGENTS.md owns the invariants. In Claude Code the independent path is a Codex
subprocess — a genuinely different model family, which a Claude teammate
reviewing Claude's work never was. The live ui-test route remains the final
proof for chatbot-facing behaviour.
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.
- 2mo ago First seen · 50 lines · 506 tokens per session scan A ed225c31894b
TinyAssets CLAUDE.md is an instructions file published in the GitHub repository Jonnyton/TinyAssets (1 stars, last pushed 1mo ago), licensed MIT. It adds 506 tokens to every session, about $0.0020 per session on Opus 5.5. 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.
TinyAssets CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| TinyAssets CLAUDE.mdJonnyton/TinyAssets | Instructions file | 1 | 1mo ago | MIT | A | 506 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |