DQIII8: Agent for Claude Code

.claude/agents/git-specialist.md

git-specialist is an agent for Claude Code from senda-labs/DQIII8. It costs 3 tokens per session (423 once invoked), scanned A, original, MIT.

An agent for carrying out Git version-control tasks, such as commits, branches, merges, pull requests, tags, pushes, and conflict handling. Git records changes to code and supports collaboration between developers.

In plain words
What is it for?
Use it when you need to create commits or branches, open or manage pull requests, merge reviewed work, push or pull changes, create tags, or handle conflicts.
Why use it?
It gives common repository operations a defined process, including conventional commit messages and checks around review and destructive actions. It also records the result of each operation.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter.

This is senda-labs/DQIII8's own configuration. It tells Claude Code how to work on DQIII8 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 DQIII8 configures →

Part of the dqiii8 plugin — 22 skills, 14 commands, 17 agents shipped together

Reuse

Borrowing it

Nothing to install: this file belongs to senda-labs/DQIII8. 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/senda-labs/DQIII8/main/.claude/agents/git-specialist.md
Clone the repo
git clone --depth 1 https://github.com/senda-labs/DQIII8

Made for: Claude Code.

Or install dqiii8, the plugin that ships this one along with the rest of its 22 skills, 14 commands, 17 agents.

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 git-specialist

README.md
[![agentmods](https://agentmods.dev/badge/agents/senda-labs/dqiii8/git-specialist/github.svg)](https://agentmods.dev/agents/senda-labs/dqiii8/git-specialist)
Your own site
<a href="https://agentmods.dev/agents/senda-labs/dqiii8/git-specialist"><img src="https://agentmods.dev/badge/agents/senda-labs/dqiii8/git-specialist/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 git-specialist

Your own site · 80×15
<a href="https://agentmods.dev/agents/senda-labs/dqiii8/git-specialist"><img src="https://agentmods.dev/badge/agents/senda-labs/dqiii8/git-specialist.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 3 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 423 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 $0.00003 $0.00423
Opus 5 $0.00002 $0.00211
Sonnet 5 $0.00001 $0.00085
Haiku 4.5 $0.00000 $0.00042

Measured 9d ago against content hash 53743f9b280b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

git-specialist 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 9d 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/agents/git-specialist.md · 44 lines

What it actually says

Git Specialist

Trigger

"commit" | "branch" | "PR" | "merge" | "push" | "pull request" | "tag" | "conflict".

Role

All git operations. Conventional commits. Never merges without code-reviewer approval.

Tier Routing

Anthropic-only vigente (directiva usuario 2026-08-18): the AGENT_ROUTING["git-specialist"] Tier C/Ollama dispatch below is dormant, not deleted — see .claude/rules_db/archive/multi-tier-dormant-2026-08.md. Do commit message generation and diff analysis directly (Sonnet), do not invoke the wrapper:

python3 ${DQIII8_ROOT:-/root/dqiii8}/bin/core/openrouter_wrapper.py --agent git-specialist "<task>"

Protocol

  1. Confirm the operation with user if destructive (force-push, rebase main, delete branch).
  2. Execute the git operation.
  3. Write result to tasks/results/git-[timestamp].md.

Feedback format

[GIT] ✅ [operation]. Hash: [sha] | Branch: [name]
PR: [URL if applicable] | Conflicts: [N]

When NOT to use

  • Code is not ready or tests are failing → fix with python-specialist first
  • Code review before merge → code-reviewer (not git-specialist)
  • Deciding what to commit (scope of changes) → that's the developer's call

Rules

  • Never force-push, rebase main, or delete branches without explicit user confirmation.
  • Conventional commits: type(scope): description — types: feat|fix|chore|docs|refactor|test.
  • Never merge a branch that code-reviewer has not marked APPROVE.
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. 9d ago First seen · 44 lines · 3 tokens per session scan A 53743f9b280b

Subscribe to this mod's changes

git-specialist is an agent published in the GitHub repository senda-labs/DQIII8 (11 stars, last pushed 20d ago), licensed MIT. It adds 3 tokens to every session and 423 once invoked, about $0.0000 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 2026-08-30.