holocron: Command for Claude Code

.claude/commands/close-improvements.md

close-improvements is a command for Claude Code from hackerpug-ai/holocron. It costs 15 tokens per session (824 once invoked), scanned A, original, MIT.

A command that checks open improvement requests against the current code and closes the ones that are already finished.

In plain words
What is it for?
It helps maintain an accurate list of planned improvements and clean up requests that have already been shipped.
Why use it?
It removes the need to compare every old request with the code by hand, while leaving partly finished work open.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: mentions subagents; mentions Claude Code.

This is hackerpug-ai/holocron's own configuration. It tells Claude Code how to work on holocron 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 holocron configures →

Reuse

Borrowing it

Nothing to install: this file belongs to hackerpug-ai/holocron. 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/hackerpug-ai/holocron/main/.claude/commands/close-improvements.md
Clone the repo
git clone --depth 1 https://github.com/hackerpug-ai/holocron

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 close-improvements

README.md
[![agentmods](https://agentmods.dev/badge/commands/hackerpug-ai/holocron/close-improvements/github.svg)](https://agentmods.dev/commands/hackerpug-ai/holocron/close-improvements)
Your own site
<a href="https://agentmods.dev/commands/hackerpug-ai/holocron/close-improvements"><img src="https://agentmods.dev/badge/commands/hackerpug-ai/holocron/close-improvements/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 close-improvements

Your own site · 80×15
<a href="https://agentmods.dev/commands/hackerpug-ai/holocron/close-improvements"><img src="https://agentmods.dev/badge/commands/hackerpug-ai/holocron/close-improvements.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 15 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 824 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 $0.00015 $0.00824
Opus 5.5 $0.00006 $0.00330
Sonnet 5.5 $0.00003 $0.00165
Haiku 4.5 $0.00002 $0.00082

Measured 13d ago against content hash 74aff4ac0b1b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

close-improvements 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 13d 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/close-improvements.md · 78 lines

How it starts

The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/close-improvements

Audit every open improvement request in the holocron MCP against the current codebase, then auto-close the ones that evidence shows are already implemented. No approval gate — open items that have been shipped get closed; partial/not-done stay open.

Workflow

1. List open improvements

Call mcp__holocron__listImprovementsTool with { status: "open", limit: 100 }. For each returned item, capture:

  • _id
  • title and description (truncate description to ~200 chars for the audit prompt)
  • sourceScreen / sourceComponent (hints about where in the app this lives)

If the list is large (>6 items), process in parallel batches — one Explore agent per improvement, dispatched in a single message.

2. Dispatch parallel Explore agents

For each open improvement, dispatch an Explore subagent with a tight, evidence-based prompt:

I need to determine whether this improvement request has been implemented in the holocron codebase.

Improvement: {title}
Description: {description}
Source: {sourceScreen}/{sourceComponent}

Search the codebase for relevant files and return ONE of these verdicts with evidence:

- IMPLEMENTED — the improvement is fully shipped. Cite 1-3 specific file paths (with line numbers if helpful) that prove it. Be strict: partial implementations are NOT implemented.
- PARTIAL — some of it is done but key pieces are missing. Cite what's done and what's missing.
- NOT_DONE — no trace in the codebase, or the improvement describes something that clearly doesn't exist yet.

Keep your response under 100 words. Format:
VERDICT: {IMPLEMENTED|PARTIAL|NOT_DONE}
EVIDENCE:
- {file path 1}: {why this proves it}
- {file path 2}: {why this proves it}

3. Close IMPLEMENTED items

For each agent verdict of IMPLEMENTED, call mcp__holocron__closeImprovementTool (or setImprovementStatusTool with status=closed) with:

  • id: the improvement _id
  • reason: "Auto-closed by codebase audit on {YYYY-MM-DD}: {1-sentence why}"
  • evidence: array of file paths from the agent's EVIDENCE section

Read the full file on GitHub · 78 lines

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. 13d ago First seen · 78 lines · 15 tokens per session scan A 74aff4ac0b1b

Subscribe to this mod's changes

close-improvements is a command published in the GitHub repository hackerpug-ai/holocron (0 stars, last pushed 1mo ago), licensed MIT. It adds 15 tokens to every session and 824 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 2026-10-02.