keystone: Command for Claude Code

.claude/commands/keystone-verify.md

keystone-verify is a command for Claude Code from tacoda/keystone. It costs 19 tokens per session (361 once invoked), scanned A, a copy of verify, MIT.

A verification command that runs the project's available checks, such as linting, type-checking, tests, builds, rule-drift checks, and commit-message checks.

In plain words
What is it for?
Use it before committing code to run the configured verification sensors and show their actual results.
Why use it?
It provides fresh evidence that changes meet the project's technical and process requirements.

Command for Claude Code

Written for Claude Code: installed under .claude/.

This is tacoda/keystone's own configuration. It tells Claude Code how to work on keystone itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything keystone configures →

Reuse

Borrowing it

Nothing to install: this file belongs to tacoda/keystone. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/tacoda/keystone/main/.claude/commands/keystone-verify.md
Clone the repo
git clone --depth 1 https://github.com/tacoda/keystone

Made for: Claude Code.

Wrote 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.

agentmods badge for keystone-verify

README.md
[![agentmods](https://agentmods.dev/badge/commands/tacoda/keystone/keystone-verify.svg)](https://agentmods.dev/commands/tacoda/keystone/keystone-verify)
Your own site
<a href="https://agentmods.dev/commands/tacoda/keystone/keystone-verify"><img src="https://agentmods.dev/badge/commands/tacoda/keystone/keystone-verify.svg" alt="Measured on agentmods" height="20"></a>
Per session 19 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 361 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin 100% copy Near-identical to another mod in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00019 $0.00361
Opus 5 $0.00010 $0.00180
Sonnet 5 $0.00004 $0.00072
Haiku 4.5 $0.00002 $0.00036

Measured 3d ago against content hash 110203b9bdc1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

keystone-verify 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 3d 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.

Origin

This is a copy

100% identical to verify — 4 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.claude/commands/keystone-verify.md · 28 lines

What it actually says

verify

Run the verification sensors — lint, type-check, test, build, drift, commit-message. Pre-commit gate. Read .charter/guides/process/verification.md.

Activities

Run every sensor classified as runnable in .charter/corpus/state/CODEBASE_STATE.md, in this turn (no stale evidence). For each sensor:

  1. lint.charter/sensors/lint.md. Invoke the project's lint command.
  2. type-check.charter/sensors/type-check.md. Invoke the type-check command. Skip if no type checker.
  3. test.charter/sensors/test.md. Invoke the test command. Fresh run.
  4. build.charter/sensors/build.md. Invoke the build command.
  5. drift.charter/sensors/drift.md. Compare diff to loaded guides.
  6. commit-message.charter/sensors/commit-message.md. Inspect the proposed message before git commit.

Show the actual tool output for each. Do not claim a sensor passed without producing its output this turn.

Iron law

No completion claims without fresh verification evidence. Sensors must run in this turn.

On failure

Return to implementation. Do not "fix forward" inside verify. After the fix, re-invoke verify in a fresh turn.

Changes

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.

  1. 3d ago First seen · 28 lines · 19 tokens per session scan A 110203b9bdc1

Subscribe to this mod's changes

keystone-verify is a command published in the GitHub repository tacoda/keystone (44 stars, last pushed 2mo ago), licensed MIT. It adds 19 tokens to every session and 361 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to verify, differing in 4 lines, and is treated as a copy.