agentmods.dev

corpus-kb: Command for Claude Code

.claude/commands/corpus-release.md

corpus-release is a command for Claude Code from moliver28/corpus-kb. It costs 14 tokens per session (393 once invoked), scanned A, original, MIT.

A command set for moving a codebook version through assessment, review, approval, release, status checks, and comparisons. A codebook is a structured set of labels or rules used to classify data.

In plain words
What is it for?
Use it to assess a candidate, request and review a release, execute it with a named human approver, inspect its status, or compare successor versions.
Why use it?
It makes release gates, missing evidence, waivers, approvers, and the resulting audit trail explicit instead of treating release as an unchecked command.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter.

This is moliver28/corpus-kb's own configuration. It tells Claude Code how to work on corpus-kb 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 corpus-kb configures →

not rated 1repo changed 22d ago A scan 14 tokens original MIT
View source ↗ moliver28/corpus-kb
Reuse

Borrowing it

Nothing to install: this file belongs to moliver28/corpus-kb. 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/moliver28/corpus-kb/master/.claude/commands/corpus-release.md
Clone the repo
git clone --depth 1 https://github.com/moliver28/corpus-kb

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 corpus-release

README.md
[![agentmods](https://agentmods.dev/badge/commands/moliver28/corpus-kb/corpus-release/github.svg)](https://agentmods.dev/commands/moliver28/corpus-kb/corpus-release)
Your own site
<a href="https://agentmods.dev/commands/moliver28/corpus-kb/corpus-release"><img src="https://agentmods.dev/badge/commands/moliver28/corpus-kb/corpus-release/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 corpus-release

Your own site · 80×15
<a href="https://agentmods.dev/commands/moliver28/corpus-kb/corpus-release"><img src="https://agentmods.dev/badge/commands/moliver28/corpus-kb/corpus-release.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 14 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 393 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 $0.00014 $0.00393
Opus 5.5 $0.00006 $0.00157
Sonnet 5.5 $0.00003 $0.00079
Haiku 4.5 $0.00001 $0.00039

Measured 22d ago against content hash f0a59b1ad565, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

corpus-release 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 22d 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.

.claude/commands/corpus-release.md · 47 lines

What it actually says

corpus-release — the release lifecycle (v6 §6)

Walk a codebook version from draft to released codebook: assess the gates, open the draft, review the packet, execute with a named approver, and diff successors.

  • Compose EVERY gate over current evidence (writes NOTHING; not_evaluable gates are reported, never silently passed):

    corpus-kb release assess --codebook-version-id <uuid> [--profile <name>]

  • Open a draft_candidate release pinned to the current content hash:

    corpus-kb release request --codebook-version-id <uuid> --creator <you>

  • The review packet: gate evidence, failing/not_evaluable gates, waivers, and the exact next commands:

    corpus-kb release review --codebook-version-id <uuid> --release-id <release-id>

  • Execute the release (HUMAN APPROVER required; enforcement=enforce blocks unmet required gates, --waive GATE=justification records explicit waivers; a refusal exits 1 with a structured error):

    corpus-kb release release --codebook-version-id <uuid> --release-id <release-id> --approver <you>

  • Read the trail; every command takes --json:

    corpus-kb release status --codebook-version-id <uuid>
corpus-kb release compare --codebook-version-id <uuid> --old-release-id <a> --new-release-id <b>

  • All flags: corpus-kb release status --help (and each subcommand)

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. 22d ago Changed · +14 tokens per session f0a59b1ad565
  2. 25d ago First seen · 47 lines · 0 tokens per session scan A 6120b6a18166

Subscribe to this mod's changes

corpus-release is a command published in the GitHub repository moliver28/corpus-kb (1 stars, last pushed today), licensed MIT. It adds 14 tokens to every session and 393 once invoked, about $0.0001 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 2026-10-12.

Git and workflowPlanningReleases
Related

corpus-release compared with commands from other repositories

corpus-release next to 6 commands from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
corpus-releasemoliver28/corpus-kbCommand1todayMITA14Claude Code
landgmickel/flow-nextCommand717yesterdayMITA13Claude Code
qualityDesko77/claude-code-skills-1cCommand90yesterdayMITA18Claude Code
release-notesOpenHands/extensionsCommand176yesterdayMITA44Claude Code
release-managerruvnet/agentic-flowCommand838yesterdaynoneA0Claude Code
create-prdsswift/ionCommand5yesterdayMITA28Claude Code
rally-merge-prddgonzal3/rallyCommand63d agoMITA0Claude Code