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/iliaal/whetstone/agents-mdgit clone --depth 1 https://github.com/iliaal/whetstoneWrote 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/iliaal/whetstone/agents-md)<a href="https://agentmods.dev/instructions/iliaal/whetstone/agents-md"><img src="https://agentmods.dev/badge/instructions/iliaal/whetstone/agents-md.svg" alt="Measured on agentmods" 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 | $0.05645 | $0.05645 |
| Opus 5 | $0.02823 | $0.02823 |
| Sonnet 5 | $0.01129 | $0.01129 |
| Haiku 4.5 | $0.00564 | $0.00564 |
Grade A, and why
whetstone 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 4d 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 — 330 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Whetstone
Claude Code plugin for PHP/React/Python/JavaScript/TypeScript workflows. Includes the plugin (agents, commands, skills, hooks), a skill distillery, and a CLI for cross-tool conversion.
When you see a <session-commands> tag in hook context, briefly list those commands to the user at the start of your first response.
Repository structure
whetstone/
├── .claude-plugin/
│ └── marketplace.json # Marketplace catalog
├── distillery/ # Skill distillery (generate skills from skills.sh)
│ ├── scripts/
│ │ ├── distiller.py # Search, fetch, validate, eval, harvest, test
│ │ └── test_distiller.py # pytest tests for distiller
│ └── generated-skills/ # Generated skill output directory
├── scripts/
│ ├── update-metadata.sh # Update component counts in plugin.json + marketplace.json
│ ├── generate-skill-hooks.sh # Generate hook patterns from SKILL.md frontmatter
│ ├── mirror-to-ai-skills.sh # Mirror plugin skills to ai-skills public repo
│ ├── configure-codex-skill-sources.py # Disable duplicate direct sources in Codex
│ ├── install-codex-plugin.sh # Install/enable plugin, then retire duplicate sources
│ ├── refresh-codex-plugin.sh # Cachebust/reinstall Codex without dirtying release version
│ ├── sync-to-tools.sh # Symlink skills to .agents/.kilocode; retire legacy Codex links
│ └── update-plugin.sh # Update locally installed plugin to latest version
├── CHANGELOG.md # Version history
└── plugins/
└── whetstone/ # The plugin
├── .codex-plugin/
│ └── plugin.json # Codex skills-plugin metadata
├── .claude-plugin/
│ └── plugin.json # Plugin metadata
├── agents/ # Agents (all `ia-<name>.md`, flat layout)
├── shared-references/ # Cross-agent reference content loaded by agents via Read
├── commands/ # Slash commands (all `ia-<name>.md`)
│ └── references/ # Non-invocable reference content (not prefixed)
├── skills/ # Skills (all `ia-<name>/`)
│ └── ia-<skill-name>/
│ ├── SKILL.md # Skill content
│ ├── references/ # Optional supplementary docs
│ └── scripts/ # Optional bundled scripts
├── hooks/ # 1 hook (inject-skills into subagents)
└── README.md # Plugin documentation
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.
- 4d ago First seen · 330 lines · 5,645 tokens per session scan A 593cffe13493
whetstone AGENTS.md is an instructions file published in the GitHub repository iliaal/whetstone (32 stars, last pushed 5d ago), licensed MIT. It adds 5,645 tokens to every session, about $0.0282 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
platform-skills copilot-instructions.md
Copilot instructions for nitinjain999/platform-skills, covering platform engineering instructions for github copilot, version: 1.40.0, source: https://github.com/nitinjain999/platform-skills, response contract and core principles.
claude-anvil CLAUDE.md
Instructions for queelius/claude-anvil, covering claude.md, what this is, per-repo plugin scoping (context economy), three plugins say "research" and they do not overlap and plugin anatomy.
claude-sdd-plugin CLAUDE.md
Claude Code instructions for viamus/claude-sdd-plugin, covering sdd orchestrator — plugin context, fundamental rules, workflow, pipeline (automated by sdd-gen) and plugin structure.
aesth CLAUDE.md
Claude Code instructions for zircote-plugins/aesth, covering claude.md, architecture, key concepts, memory-first design and memory types.
ClaudeCode-Model-Rotator CLAUDE.md
Claude Code instructions for BheeshamKS/ClaudeCode-Model-Rotator, covering claude code multi-provider rotator - project guide, project overview, core architecture, files and key components.
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).