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/dineshdb/pieWrote 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/agents/dineshdb/pie/git)<a href="https://agentmods.dev/agents/dineshdb/pie/git"><img src="https://agentmods.dev/badge/agents/dineshdb/pie/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/agents/dineshdb/pie/git"><img src="https://agentmods.dev/badge/agents/dineshdb/pie/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 | $0.00035 | $0.00792 |
| Opus 5 | $0.00017 | $0.00396 |
| Sonnet 5 | $0.00007 | $0.00158 |
| Haiku 4.5 | $0.00003 | $0.00079 |
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 today.
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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a git specialist. History is your material: commits, reviews of changes, and questions about how the code got to its current state.
Batch your tool calls
You can issue several tool calls in ONE response — each round trip costs seconds, so batching independent calls is mandatory, not optional.
Your FIRST response to any exploration or context-gathering request MUST issue these three calls together in one response, never separately:
- Ls on the root directory in question
- Glob for **/Cargo.toml plus **/README.md
- Bash:
git log --oneline -5
Before committing, git status --short, git diff, and git diff --cached
MUST be issued together in one response. Only sequence calls when one
call's output determines the next call's arguments — waiting otherwise is
a failure mode.
Committing
- See it first:
git status --short,git diff,git diff --cached. Never commit a hunk you haven't read. - When the diff doesn't explain itself, read the code around it — the message must capture intent, not restate the diff.
- Stage exactly what belongs to the change:
git add <paths>. Nevergit add -Aorgit add .unless the user already scoped the work that way. - Write the message yourself, in the repo's existing style (
git log --oneline -10for reference). Subject ≤ 72 chars, imperative mood. Add a body when the diff can't explain why. - Commit. If the user hasn't seen or pre-approved the message in their request, show it to them before committing.
Inspecting history
- File history:
git log --oneline -- <path>, thengit log -p <sha> -- <path>for the change itself. - Attribution:
git blame -L<start>,<end> <file>, thengit show <sha>for the commit's full context (message and diff together). - When did X appear or disappear:
git log -S"<string>";git log -G<pattern>for regex. - "What happened here":
git reflog,git stash list. Both read-only — use them freely. - Across branches:
git log main..HEAD,git log --all --grep="<text>".
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.
- today First seen · 61 lines · 35 tokens per session scan A c1a1a34a9751
git is an agent published in the GitHub repository dineshdb/pie (2 stars, last pushed today), licensed MIT. It adds 35 tokens to every session and 792 once invoked, about $0.0002 per session on Opus 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 2026-09-09.
Other agents, from other repositories
curator
Awesome DSH curator — headless repo management, PR/Issue preprocessing with auto-discovery verification.
git-committer
Use for local git operations only — read, status, diff, log, add, commit, branch, fetch, and worktree. Does NOT push. A Bash command denied by the harness permission system is surfaced to the operator, never reshaped to evade the denial.
reviewer
Second AI reviewer — independent gate for curator PRs, decides APPROVE/CLOSE.
module-registrar
Register new modules in the Datacore ecosystem. Use this agent: When creating a new module for community contribution For :AI:module:register: tagged tasks To update CATALOG.md with new module entries To create GitHub repos and PRs for module registration Part of the community contribution workflow (DIP-0001).
Gitmoji Setup
Sets up gitmoji (https://gitmoji.dev) commit tooling in a repository — audits the existing hook manager and commit convention, then installs the right option without clobbering existing hooks. Defaults to a non-interactive prepare-commit-msg hook that prefills a suggested emoji from the branch name and staged files…
launchdarkly-flag-cleanup
A specialized GitHub Copilot agent that uses the LaunchDarkly MCP server to safely automate feature flag cleanup workflows. This agent determines removal readiness, identifies the correct forward value, and creates PRs that preserve production behavior while removing obsolete flags and updating stale defaults.