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.
curl -O https://raw.githubusercontent.com/senda-labs/DQIII8/main/.claude/agents/git-specialist.mdgit clone --depth 1 https://github.com/senda-labs/DQIII8Wrote 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/senda-labs/dqiii8/git-specialist)<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.
<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>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 | $0.00003 | $0.00423 |
| Opus 5 | $0.00002 | $0.00211 |
| Sonnet 5 | $0.00001 | $0.00085 |
| Haiku 4.5 | $0.00000 | $0.00042 |
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.
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
- Confirm the operation with user if destructive (force-push, rebase main, delete branch).
- Execute the git operation.
- 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.
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.
- 9d ago First seen · 44 lines · 3 tokens per session scan A 53743f9b280b
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.
Other agents, from other repositories
Jira Workflow Steward
Expert delivery operations specialist who enforces Jira-linked Git workflows, traceable commits, structured pull requests, and release-safe branch strategy across software teams.
ship-workflow
Automated ship/release specialist. Merges main, runs tests, reviews the diff, bumps version, generates changelog, creates bisectable commits, pushes, and opens a PR.
Git Workflow Master
Expert in Git workflows, branching strategies, and version control best practices including conventional commits, rebasing, worktrees, and CI-friendly branch management.
pr-submitter
Creates a git branch, commits a cask, and opens a PR to homebrew-cask.
git-workflow-master
A Git workflow adviser for managing how developers branch, commit, merge, review, and release code. Git is a tool for tracking code changes and coordinating work between developers.
shipper
Git hygiene and release specialist. Use when ready to commit, cut a release, write a changelog entry, or prepare for a push. Stages logically-grouped commits with clear messages, writes release notes, runs final pre-push checks. Never pushes, tags, or deletes on its own — it reports the exact command for the lead to…