tempo-filler-mcp-server: Command for Claude Code

.claude/commands/update-understanding.md

update-understanding is a command for Claude Code from TRANZACT/tempo-filler-mcp-server. It costs 0 tokens per session (351 once invoked), scanned A, original, ISC.

A command for loading a project's existing documentation, specifications, source-file list, and implementation context into an AI coding session.

In plain words
What is it for?
Use it when the agent needs a comprehensive overview before answering questions or changing code.
Why use it?
It reduces the chance that the agent will work from an incomplete understanding of the project's requirements or architecture.

Command for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions subagents.

This is TRANZACT/tempo-filler-mcp-server's own configuration. It tells Claude Code how to work on tempo-filler-mcp-server 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 tempo-filler-mcp-server configures →

Reuse

Borrowing it

Nothing to install: this file belongs to TRANZACT/tempo-filler-mcp-server. 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/TRANZACT/tempo-filler-mcp-server/main/.claude/commands/update-understanding.md
Clone the repo
git clone --depth 1 https://github.com/TRANZACT/tempo-filler-mcp-server

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 update-understanding

README.md
[![agentmods](https://agentmods.dev/badge/commands/tranzact/tempo-filler-mcp-server/update-understanding/github.svg)](https://agentmods.dev/commands/tranzact/tempo-filler-mcp-server/update-understanding)
Your own site
<a href="https://agentmods.dev/commands/tranzact/tempo-filler-mcp-server/update-understanding"><img src="https://agentmods.dev/badge/commands/tranzact/tempo-filler-mcp-server/update-understanding/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 update-understanding

Your own site · 80×15
<a href="https://agentmods.dev/commands/tranzact/tempo-filler-mcp-server/update-understanding"><img src="https://agentmods.dev/badge/commands/tranzact/tempo-filler-mcp-server/update-understanding.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 351 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 $0.00000 $0.00351
Opus 5 $0.00000 $0.00176
Sonnet 5 $0.00000 $0.00070
Haiku 4.5 $0.00000 $0.00035

Measured 11d ago against content hash 968bfd161dd0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

update-understanding 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 11d 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/update-understanding.md · 26 lines

What it actually says

Project Understanding Update

To ensure the LLM is always primed with complete and comprehensive project context, follow these steps:

  1. Mandatory Resource Ingestion
  • Ingest the full content of all existing README.md files for project overview and usage instructions.
  • Ingest the full content of PROJECT_UNDERSTANDING.md for a high-level summary of the project and its components.
  • Ingest every file from the specs directory for specifications and requirements, reading each file in its entirety. Most of this specs have already been implemented, so this will give you context to understand the code you will read next.
  • List every file from all src directories using git ls-files, and read each file completely. Use sub-agents using Sonnet and Haiku to give you summaries/understanding of each file and folder so your context window does not fill up with the code.
  1. Analysis & Comprehension
  • Analyze all ingested resources in their entirety to develop a thorough understanding of the project's goals, features, functionality, architecture, coding standards, and requirements.
  • Be prepared to answer questions or generate code that strictly follows the project's guidelines and objectives.
  1. Documentation Maintenance
  • Update PROJECT_UNDERSTANDING.md to reflect any new insights or changes in project understanding. If the file does not exist, create it.
    • Do not add a section for this priming snapshot, make the updates in place.
    • Make sure the updated document still makes sense wholistically.

Note:
Do not modify any files other than PROJECT_UNDERSTANDING.md.
Always prioritize clarity, completeness, and alignment with project standards when summarizing or generating content.

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. 11d ago First seen · 26 lines · 0 tokens per session scan A 968bfd161dd0

Subscribe to this mod's changes

update-understanding is a command published in the GitHub repository TRANZACT/tempo-filler-mcp-server (5 stars, last pushed 4mo ago), licensed ISC. It costs nothing until one of its globs matches a file; then it loads 351 tokens. 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 2026-08-31.