keystone-new-corpus

keystone-new-corpus is a skill for Claude Code, Codex from tacoda/keystone. It costs 16 tokens per session (388 once invoked), scanned A, original, MIT.

A command that creates a starter file for a corpus entry: the detailed reasoning behind a project rule. The file is stored under the project’s .charter/corpus directory and can be linked from a guide.

In plain words
What is it for?
Use it when adding reasoning to an existing guide or creating a standalone explanation of a rule’s failure cases, trade-offs, and references.
Why use it?
It avoids manually creating the required file path and structure when documenting why a rule exists.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: model in frontmatter.

Good fit Use it when adding reasoning to an existing guide or creating a standalone explanation of a rule’s failure cases, trade-offs, and references.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/tacoda/keystone/keystone-new-corpus
Install

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.

Any agent
npx skills add tacoda/keystone --skill keystone-new-corpus
Clone the repo
git clone --depth 1 https://github.com/tacoda/keystone

Made for: Claude Code, Codex.

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-new-corpus

README.md
[![agentmods](https://agentmods.dev/badge/skills/tacoda/keystone/keystone-new-corpus/github.svg)](https://agentmods.dev/skills/tacoda/keystone/keystone-new-corpus)
Your own site
<a href="https://agentmods.dev/skills/tacoda/keystone/keystone-new-corpus"><img src="https://agentmods.dev/badge/skills/tacoda/keystone/keystone-new-corpus/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.

agentmods 80×15 button for keystone-new-corpus

Your own site · 80×15
<a href="https://agentmods.dev/skills/tacoda/keystone/keystone-new-corpus"><img src="https://agentmods.dev/badge/skills/tacoda/keystone/keystone-new-corpus.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 16 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 388 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 original No closer match found 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 $0.00016 $0.00388
Opus 5 $0.00008 $0.00194
Sonnet 5 $0.00003 $0.00078
Haiku 4.5 $0.00002 $0.00039

Measured 10d ago against content hash 713f32886e92, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

keystone-new-corpus 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 10d 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.

.charter/skills/keystone-new-corpus/SKILL.md · 59 lines

What it actually says

keystone:new-corpus — scaffold a corpus entry

A corpus entry is the long-form reasoning behind a rule. It lives at .charter/corpus/<topic>/<name>.md and is opened only when a guide's traces: (or a prose forward-link) points at it.

Most authors use keystone:new-guide, which scaffolds both the guide and its paired corpus in one shot. Reach for keystone:new-corpus only when adding reasoning to an existing guide that lacks one, or when the corpus stands alone (rare).

Run

keystone new corpus <topic>/<name>

Example:

keystone new corpus idioms/rails/migrations
# writes .charter/corpus/idioms/rails/migrations.md

After scaffolding

  1. Fill in the body — the failure modes the paired rule guards against, the trade-offs, the references that informed it.
  2. Confirm the paired guide forward-links to this corpus entry (either via traces: in frontmatter or a prose For reasoning, see ... footer).
  3. Run keystone index to refresh the descriptor surface.

Full port contract: docs/ports/corpus.md.

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. 10d ago First seen · 59 lines · 16 tokens per session scan A 713f32886e92

Subscribe to this mod's changes

keystone-new-corpus is a skill published in the GitHub repository tacoda/keystone (44 stars, last pushed 2mo ago), licensed MIT. It adds 16 tokens to every session and 388 once invoked, about $0.0001 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.

Related

Other skills, from other repositories

portaljs-new-portal

Scaffold a new PortalJS data portal from a brief. Copies the canonical template from examples/portaljs-catalog and substitutes project tokens. Use when starting a brand-new data portal project from scratch.

datopian/portaljs · 46 tokens

workflow-creation

Create a new Stencila workflow. Use when asked to create, write, scaffold, or set up a workflow directory or WORKFLOW.md file. Covers workflow discovery, duplicate-name checks, ephemeral workflows, WORKFLOW.md frontmatter, DOT pipeline authoring, goals, agents, branching, composition, and validation.

stencila/stencila · 67 tokens

agent-creation

Create a new Stencila agent. Use when asked to create, write, scaffold, or set up an agent directory or AGENT.md file. Covers workspace and user-level agents with model, provider, tool, trust, and MCP configuration.

stencila/stencila · 53 tokens

skill-creation

Create a new Stencila workspace skill. Use when asked to create, write, or scaffold a SKILL.md file or skill directory.

stencila/stencila · 32 tokens

design-import

Scaffolds React components from a Claude Design handoff bundle and stops at files on disk: no stories, no tests, no pull request. Use when handed a claude.ai/design URL or a local bundle file; when that same scaffold should carry on through test generation, browser verification and an opened PR, run /ork:design-ship…

yonatangross/orchestkit · 74 tokens

plugin-init

A project starter for creating Zhin.js plugins, which are installable packages that extend the Zhin.js bot framework. It sets up the required files, folders, package metadata, entry point, and documentation.

zhinjs/zhin · 56 tokens