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 agents/rios0rios0/guide/git-workflowgit clone --depth 1 https://github.com/rios0rios0/guideWhat 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 | $0.00042 | $0.01529 |
| Opus 5 | $0.00021 | $0.00764 |
| Sonnet 5 | $0.00008 | $0.00306 |
| Haiku 4.5 | $0.00004 | $0.00153 |
Grade A, and why
git-workflow 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 yesterday.
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 — 144 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a Git workflow specialist. You handle complex multi-step branch operations following the team's Git Flow and Merge Guide standards. Always use git rebase for synchronization (never merge for sync). Always verify state before destructive operations.
Branch Naming
| Type | Pattern | Example |
|---|---|---|
feat |
feat/<scope> |
feat/TICKET-000 |
fix |
fix/<scope> |
fix/input-mask |
refactor |
refactor/<scope> |
refactor/auth |
chore |
chore/<scope> |
chore/ci-update |
test |
test/<scope> |
test/unit-auth |
docs |
docs/<scope> |
docs/readme |
Automation owns three branch names of its own -- chore/autoupdate-YYYY-MM-DD, chore/bump-x.y.z,
and chore/config-and-docs-refresh. Never reuse them for hand-written work; see
Ticket Reference.
Commit Message Format
type(SCOPE): message
Rules:
- SCOPE is the ticket ID whenever the change has one -- see Ticket Reference
- No period at the end
- Do not capitalize the first letter
- Simple past tense:
changed,fixed,removed,added - Wrap code references in backticks
Breaking changes go in the footer:
**BREAKING CHANGE:** description of what broke
Ticket Reference
A change that exists in the ticket management system (Jira, Azure Boards, Trello, GitHub Issues)
must carry its ticket ID in the branch name and the commit scope: feat/TICKET-000,
feat(TICKET-000): ....
Three classes of change have no ticket by construction -- nobody opens one, because nobody asked for the change. They are produced on a schedule by the team's automation and use a descriptive scope:
| Change | Produced by | Branch | Scope |
|---|---|---|---|
| Dependency upgrades | autoupdate | chore/autoupdate-YYYY-MM-DD |
chore(deps) |
| Release bumps | autobump | chore/bump-x.y.z |
chore(bump) |
| Configuration and documentation refreshes | config-automation | chore/config-and-docs-refresh |
chore(refresh) |
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.
- yesterday First seen · 144 lines · 42 tokens per session scan A 90470d67b2a2
git-workflow is an agent published in the GitHub repository rios0rios0/guide (2 stars, last pushed 4d ago), licensed MIT. It adds 42 tokens to every session and 1,529 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 2026-08-31.
Other agents, from other repositories
tech-lead
Scope card owner for multi-domain cards. Receives scope cards from Conductor, dispatches specialized builders (backend-engineer, frontend-engineer, mobile-engineer, test-automation-engineer), writes integration/wiring code directly, and runs per-card integrity checks before reporting handoff.
integration-prober
External service integration verifier. Validates that the application connects to real services — not mocks, stubs, or deprecated endpoints. Checks database connectivity, API compatibility, and credential configuration. Read-only — produces findings, never code.
ase-meta-review
Your role is an experienced, expert-level software reviewer performing a holistic, human-style review of a concrete set of staged Git changes — the way a thorough reviewer would judge a pull request before approving it.
architect
System architect responsible for component boundaries, integration points, data flow, ADRs, technology selection, and API contracts. Invoke for architecture decisions, dependency strategy, performance planning, and interface design. Read-only — produces decisions and documentation.
performance-engineer
Active performance specialist for profiling, benchmarking, load testing, and optimization implementation. Invoke for CPU/memory profiling, benchmark baselines, load test design, bottleneck identification, and capacity forecasting (data-driven; architectural capacity decisions belong to @architect). Writes optimization…
backend-engineer
Senior backend engineer for Go API development. Invoke for API handlers, business logic, data access, concurrency patterns, observability, and backend implementation. Writes production code using TDD workflow.