Borrowing it
Nothing to install: this file belongs to tbhb/vale-ai-tells. 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/tbhb/vale-ai-tells/main/AGENTS.mdgit clone --depth 1 https://github.com/tbhb/vale-ai-tellsWrote 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/tbhb/vale-ai-tells/agents-md)<a href="https://agentmods.dev/instructions/tbhb/vale-ai-tells/agents-md"><img src="https://agentmods.dev/badge/instructions/tbhb/vale-ai-tells/agents-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/tbhb/vale-ai-tells/agents-md"><img src="https://agentmods.dev/badge/instructions/tbhb/vale-ai-tells/agents-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 | $0.00967 | $0.00967 |
| Opus 5 | $0.00483 | $0.00483 |
| Sonnet 5 | $0.00193 | $0.00193 |
| Haiku 4.5 | $0.00097 | $0.00097 |
Grade A, and why
vale-ai-tells 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.
How it starts
The opening of the file, as written. The whole thing — 34 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent instructions
Guidance for AI coding agents working in this repository. Read it alongside the per-tool documentation and any memory files the harness loads.
Commit messages
Write Conventional Commits (type(scope): subject) with a DCO Signed-off-by trailer, and keep the subject under 80 characters. AI assistance is credited with a kernel-style Assisted-by: AGENT:VERSION [TOOL] trailer placed before the sign-off. Never credit a model through Co-authored-by.
Draft every message in a repo-root COMMIT_AGENTMSG file before you run git commit. A gitignore entry keeps that file out of history, so it serves purely as a scratchpad:
- Write the full message (subject, body, and trailers) to
COMMIT_AGENTMSG. - Run
mise run lint-commit-msgand resolve whatever it reports. - Commit the validated draft with
git commit -s -F COMMIT_AGENTMSG.
The commit-msg stage runs four hooks from the shared repotools repository: commitlint (the Conventional Commits format and length bounds), commit-trailers (the trailer format and order), vale-commit-msg (prose, under this repo's own ai-tells and ai-tells-commits styles), and cspell-commit-msg (spelling). Run mise run repotools:prek-install once so the hooks run on every commit.
That hook stage is the real gate. mise run lint-commit-msg only previews it, so a clean recipe run predicts a clean commit without replacing the hook.
Prose lint output
The toolchain defaults to the agent template: mise run lint-prose, mise run lint-messages, and the vale pre-commit hook all pass --output=ai-tells-agent.tmpl. Name the flag yourself only when invoking vale directly. The template prints one self-contained line per finding (location, severity, rule, the exact matched text, and the replacement parameter when the rule defines one) plus a totals line, so you can apply fixes without re-reading context through separate commands. Empty output means a clean run, and the exit code reports the result.
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 Changed · -2 tokens per session a6e2d12a3bb2
- 3d ago Changed · -1 tokens per session 89617c5fbae9
- 9d ago First seen · 34 lines · 970 tokens per session scan A 4488d7bcf307
vale-ai-tells AGENTS.md is an instructions file published in the GitHub repository tbhb/vale-ai-tells (87 stars, last pushed today), licensed MIT. It adds 967 tokens to every session, about $0.0048 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
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
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.
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).
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).
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.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.