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.
curl -O https://raw.githubusercontent.com/TRANZACT/tempo-filler-mcp-server/main/.claude/commands/update-understanding.mdgit clone --depth 1 https://github.com/TRANZACT/tempo-filler-mcp-serverWrote 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.
[](https://agentmods.dev/commands/tranzact/tempo-filler-mcp-server/update-understanding)<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.
<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>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00000 | $0.00351 |
| Opus 5.5 | $0.00000 | $0.00140 |
| Sonnet 5.5 | $0.00000 | $0.00070 |
| Haiku 4.5 | $0.00000 | $0.00035 |
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 2mo 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.
What it actually says
Project Understanding Update
To ensure the LLM is always primed with complete and comprehensive project context, follow these steps:
- Mandatory Resource Ingestion
- Ingest the full content of all existing
README.mdfiles for project overview and usage instructions. - Ingest the full content of
PROJECT_UNDERSTANDING.mdfor a high-level summary of the project and its components. - Ingest every file from the
specsdirectory 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
srcdirectories usinggit 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.
- 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.
- Documentation Maintenance
- Update
PROJECT_UNDERSTANDING.mdto 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.
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.
- 2mo ago First seen · 26 lines · 0 tokens per session scan A 968bfd161dd0
update-understanding is a command published in the GitHub repository TRANZACT/tempo-filler-mcp-server (5 stars, last pushed 6mo 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.
update-understanding compared with commands from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| update-understandingTRANZACT/tempo-filler-mcp-server | Command | 5 | 6mo ago | ISC | A | 0 | Claude Code |
| minutes-ideassilverstein/minutes | Command | 1.6k | yesterday | MIT | A | 48 | Claude Code, OpenCode |
| learnReflexioAI/claude-smart | Command | 791 | 3d ago | Apache-2.0 | A | 14 | Claude Code |
| memory-storeverygoodplugins/mcp-automem | Command | 66 | yesterday | MIT | A | 10 | Claude Code |
| analyze-contextRohiRIK/OpenLtm | Command | 29 | 8d ago | MIT | A | 39 | Claude Code |
| cc-memoryTheLobbi/claude | Command | 21 | 7d ago | MIT | A | 0 | Claude Code |
| lians-recallLians-ai/Lians | Command | 17 | 5d ago | Apache-2.0 | A | 19 | Claude Code |