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.
npx agentmods add commands/letitbk/claude-academic-setup/updates-gitgit clone --depth 1 https://github.com/letitbk/claude-academic-setupWhat 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 | $0.00000 | $0.00672 |
| Opus 5 | $0.00000 | $0.00336 |
| Sonnet 5 | $0.00000 | $0.00134 |
| Haiku 4.5 | $0.00000 | $0.00067 |
Grade A, and why
updates-git 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 3d 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.
How it starts
The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are documenting project progress and committing changes after a major analysis or pipeline step.
Context from user (if provided)
$ARGUMENTS
Step 1: Understand what changed
Run these in parallel:
git diff --stat— see which files were modifiedgit diff --staged --stat— see what's already stagedgit status— see untracked filesgit log --oneline -5— recent commit style
Also review the current conversation history for context about what work was done in this session.
Step 2: Identify documentation updates needed
Check each file and update ONLY sections that need to change based on the actual work done. Do NOT fabricate progress or results.
README.md
- Pipeline table (lines ~39-55): Update status column (Pending → Done) and Key Output for any completed steps.
- Next Steps section: Remove completed items, add any newly identified next steps.
- Other sections: Only update if the work directly affects them (e.g., new dictionary version, new data source).
CLAUDE.md
- Pipeline Progress table (lines ~65-83): Mirror README pipeline status updates.
- Key Files: Add any new important files created during this session.
- Do NOT change API docs, CLI docs, or coding conventions unless they actually changed.
.claude/napkin.md
- Corrections table: Add any new mistakes/corrections discovered this session.
- Patterns That Work / Don't Work: Add newly confirmed patterns.
- Domain Notes: Update if new domain knowledge was established.
- Do NOT duplicate entries that already exist.
Auto-memory (MEMORY.md)
- Find and update the project's auto-memory MEMORY.md file (under
~/.claude/projects/) if:- A pipeline step status changed
- New stable patterns were confirmed across multiple interactions
- Key file paths or conventions changed
- Keep MEMORY.md under 200 lines.
Step 3: Make the edits
- Use the Edit tool for surgical changes. Do NOT rewrite entire files.
- Match existing formatting and style exactly.
- Only change lines that reflect actual new information.
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.
- 3d ago First seen · 65 lines · 0 tokens per session scan A 5811cb0283d3
updates-git is a command published in the GitHub repository letitbk/claude-academic-setup (42 stars, last pushed 2mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 672 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 2026-08-30.
Other commands, from other repositories
speckit.git.commit
Auto-commit changes after a Spec Kit command completes.
commit-all
Group all changes semantically and commit each group separately.
commit
Based on the above changes, create a single git commit.
commit
Safe git commit practices for MindRoom.
commit
智能生成 Git 提交信息并提交.
commit
Create a Conventional Commit with signoff.