Borrowing it
Nothing to install: this file belongs to dbhq-uk/verve-skill. 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/dbhq-uk/verve-skill/main/AGENTS.mdgit clone --depth 1 https://github.com/dbhq-uk/verve-skillWrote 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/dbhq-uk/verve-skill/agents-md)<a href="https://agentmods.dev/instructions/dbhq-uk/verve-skill/agents-md"><img src="https://agentmods.dev/badge/instructions/dbhq-uk/verve-skill/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/dbhq-uk/verve-skill/agents-md"><img src="https://agentmods.dev/badge/instructions/dbhq-uk/verve-skill/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 | $0.02326 | $0.02326 |
| Opus 5.5 | $0.00930 | $0.00930 |
| Sonnet 5.5 | $0.00465 | $0.00465 |
| Haiku 4.5 | $0.00233 | $0.00233 |
Grade A, and why
verve-skill 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 1mo 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 — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Guidance for AI agents (and people) working in this repository.
What this is
The verve skill for AI coding agents - strip AI tells from prose and put a human voice back, in British or American English. It follows the Agent Skills layout (skills/<name>/SKILL.md) and ships as a Claude Code plugin.
Layout
.claude-plugin/plugin.json # plugin manifest
skills/verve/SKILL.md # the skill (agent-facing instructions)
skills/verve/references/ # the tell catalogue, wordlists, tone presets and over-correction, varieties, audience, overshare, preferences, worked examples
install.sh / install-codex.sh # local symlink installers (Claude / Codex)
prompts/ # paste-in messages: install, and a repo prose audit
evals/ # the corpus, its runner, and committed runs - not shipped, not installed
docs/design/ # dated design records: what was decided and why
docs/research/ # decision research, one folder per run; index.md is the dispatcher
Nothing under skills/ is executable. The skill is prose: instructions and
reference material, with no code at all, and CI asserts it. The absence of a
runtime is a feature people can verify at a glance, so if you are about to add a
script there, be certain the job genuinely cannot be done by instructions.
evals/ is the one exception, and it sits outside skills/ for exactly that
reason. It exists because there is no offline way to assert that a fact survived
a rewrite: something has to do the rewrite. Nobody installs it, and it is not
part of what ships.
The constraints that must not be broken
Everything else here is a preference. These are not.
1. Meaning is a veto. The skill's hard constraints - every fact, number, name, date and citation survives; technical terms keep their exact wording; nothing is invented; the argument keeps its claims - outrank every other instruction in SKILL.md, and they outrank anything you add to references/. A rewrite that reads beautifully and drops a figure has failed. If you are editing a pattern and cannot tell whether it costs meaning, it does; leave it out.
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.
- 1mo ago Changed · -2 tokens per session 9f0ac0689202
- 1mo ago Changed · +4 lines · +391 tokens per session 8dc8b5fdca9c
- 1mo ago Changed · +1 lines · +247 tokens per session a3f254fcaf59
- 1mo ago Changed · +56 tokens per session 32da99321641
- 1mo ago Changed · +2 lines · +114 tokens per session ff6eaddf0929
- 1mo ago Changed · +15 lines · +537 tokens per session e7a6274f92ef
- 2mo ago First seen · 54 lines · 983 tokens per session scan A 2055cabc908b
verve-skill AGENTS.md is an instructions file published in the GitHub repository dbhq-uk/verve-skill (0 stars, last pushed 25d ago), licensed MIT. It adds 2,326 tokens to every session, about $0.0093 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.
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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 copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.