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/jahala/tilth/agents-mdgit clone --depth 1 https://github.com/jahala/tilthWhat 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 | $0.00421 | $0.00421 |
| Opus 5 | $0.00211 | $0.00211 |
| Sonnet 5 | $0.00084 | $0.00084 |
| Haiku 4.5 | $0.00042 | $0.00042 |
Grade A, and why
tilth 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.
What it actually says
tilth — code intelligence MCP server. Replaces grep, cat, find, ls with AST-aware equivalents.
PATHS: DO NOT pass a relative path or scope without also setting root (absolute) — the server cannot see your shell cwd, so bare relative paths are refused. Absolute paths always work; omitting path/scope searches the project the server was launched in. DO NOT pass a file as scope — scope is a directory; to search one file, set glob to that file's path.
To explore code, always search first. tilth_search finds definitions, usages, and file locations in one call. Usage: tilth_search(query: "handleRequest"). tilth_list is ONLY for listing directory contents when you have no symbol or text to search for. DO NOT use Read if content is already shown in expanded search results. DO NOT use Grep, Read, or Glob. Always use the better tools tilth_search (grep), tilth_read (read), tilth_list (glob).
Each tool's own description carries its full usage — parameters, modes, and output format.
To search code, use tilth_search instead of Grep or Bash(grep/rg). To read files, use tilth_read instead of Read or Bash(cat). To find files, use tilth_list instead of Glob or Bash(find/ls). To check what changed, use tilth_diff instead of Bash(git diff/git log). DO NOT use Bash(git diff) or Bash(git log --patch). Use tilth_diff instead. DO NOT re-read files already shown in expanded search results.
tilth_write replaces the host Edit and Write tools. Its full usage — hash/overwrite/append modes, hash anchors from tilth_read, grouping multi-file writes into one call, per-file partial success — is in the tilth_write tool description. DO NOT use the host Edit or Write tool. Use tilth_write for all writes.
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 · 23 lines · 421 tokens per session scan A 2ee52805bb6d
tilth AGENTS.md is an instructions file published in the GitHub repository jahala/tilth (333 stars, last pushed 2d ago), licensed MIT. It adds 421 tokens to every session, about $0.0021 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 2026-08-30.
Other instructions, from other repositories
cocoindex AGENTS.md
AGENTS.md instructions for cocoindex-io/cocoindex, covering agents.md, build and test commands, building, testing and code formatting and linting.
apm python.instructions.md
Python development guidelines.
framework AGENTS.md
Instructions for ai-driven-dev/framework, covering agents.md, behavior, communication, action and memory management.
packmind packmind-rest-api-endpoint-design.instructions.md
Instructions for PackmindHub/packmind: Conventions for designing REST API endpoints that are predictable, self-documenting, and aligned with distinct business actions. Favors dedicated action endpoints over generic status updates, and rout... .
Commit Message
Comprehensive Conventional Commits guidelines for openwebui-extensions.
SwarmAI CLAUDE.md
Instructions for xg-gh-25/SwarmAI, covering claude.md, before you push — the local quality gate, commit identity, dev commands and conventions & invariants.