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.
git clone --depth 1 https://github.com/parzival1l/AltruWrote 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/rules/parzival1l/altru/git)<a href="https://agentmods.dev/rules/parzival1l/altru/git"><img src="https://agentmods.dev/badge/rules/parzival1l/altru/git/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/rules/parzival1l/altru/git"><img src="https://agentmods.dev/badge/rules/parzival1l/altru/git.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 | $0.00018 | $0.00590 |
| Opus 5.5 | $0.00007 | $0.00236 |
| Sonnet 5.5 | $0.00004 | $0.00118 |
| Haiku 4.5 | $0.00002 | $0.00059 |
Grade A, and why
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 1mo 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 — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Altru — Git and Activity Logging
When to use this rule: Whenever you finish a task, touch versioned project files, or the user asks about history or commits.
Branch-First (Pull Requests)
For changes intended for GitHub as a PR:
git fetch originand check outmain,git pullto start current.git checkout -b cursor/<short-description>— informative name, prefixcursor/for agent-driven work.- Make edits, then stage / commit only after explicit user confirmation.
- After commit,
git push -u origin <branch>only after explicit user confirmation, then open a PR (compare →main).
Exception: Direct commits on main only when the user explicitly requests it (e.g. hotfix). Still requires confirmation before git commit / git push.
Commit and Push Rules
- Never run
git add/git commitwithout explicit user confirmation each time. - Never run
git pushwithout explicit user confirmation each time. No auto-push. - Multiple prompts without committing is normal — do not assume the user wants to commit.
- After completing substantive work, ask whether to commit (offer a suggested message). If declined, continue; ask again after the next batch of changes.
- Commit and push are always separate offers unless the user explicitly says both in one message.
Typical Flow
- Finish task → update
docs/ACTIVITY.md. - Ask whether to stage and commit now (suggest a message). Wait for confirmation.
- If they commit and want remote updated → ask again separately before
git push.
docs/ACTIVITY.md Entries
Append a timestamped entry to docs/ACTIVITY.md after every substantive set of changes.
Entry Format
## YYYY-MM-DD HH:MM ET — [brief title]
- **Files:** `path/one`, `path/two`
- **What:** …
- **Why:** …
- **Commands:** … (or "none")
Time: Always include clock time in US Eastern Time with suffix ET.
Get current time: TZ=America/New_York date '+%Y-%m-%d %H:%M'
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.
- 1mo ago First seen · 60 lines · 18 tokens per session scan A 8d400bbc0902
git is a cursor rule published in the GitHub repository parzival1l/Altru (2 stars, last pushed 5mo ago), licensed MIT. It adds 18 tokens to every session and 590 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 2026-08-31.
Other cursor rules, from other repositories
rebase-only-merged-agents
When rebasing after a merge, only rebase the agents whose branches you just merged. Do not rebase agents that are still running.
iris
GitHub operations specialist — branches, pull requests, issues, releases, tags. Called by zeus after review. Never pushes or merges without explicit human approval. Integrates with VS Code GitHub Pull Requests extension.
git-workflow
Rules for git operations, commit strategy, and GitHub CLI usage.
release-checklist
What to update with each code change or version release.
git-workflow
Git commit format and PR process - conventional commits.
branching-merging-strategy
This is a set of instructions to the AI Assistant for branching and merging strategy.