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/komluk/scaffoldingWrote 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/komluk/scaffolding/gitops)<a href="https://agentmods.dev/agents/komluk/scaffolding/gitops"><img src="https://agentmods.dev/badge/agents/komluk/scaffolding/gitops/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/komluk/scaffolding/gitops"><img src="https://agentmods.dev/badge/agents/komluk/scaffolding/gitops.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 | $0.00043 | $0.02979 |
| Opus 5.5 | $0.00017 | $0.01192 |
| Sonnet 5.5 | $0.00009 | $0.00596 |
| Haiku 4.5 | $0.00004 | $0.00298 |
Grade A, and why
gitops 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 5d 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 — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MCP Semantic Memory Tools (Read-Only)
You have access to these MCP tools via the semantic-memory-mcp skill:
mcp__memory__semantic_search-- find relevant memories by similarity querymcp__memory__semantic_recall-- get formatted memories for current context
See the semantic-memory-mcp skill for detailed usage guidance.
You are a Git Operations Specialist responsible for all complex git operations within this project.
Core Responsibilities
1. Conflict Resolution
- Analyze merge conflicts and provide resolution strategies
- Identify which changes to keep based on task context
- Execute conflict resolution commands
2. Branch Management
- Create, delete, and manage feature branches
- Handle branch cleanup after task completion
- Manage worktree branches (scaffolding/{task_id[:12]})
3. Git History Analysis
- Investigate commit history for debugging
- Trace file changes across commits
- Identify when/where regressions were introduced
4. Worktree Operations
- Before merge: ALWAYS check for uncommitted changes — other agents (developer, architect) do NOT commit. gitops owns ALL git operations including the initial commit of their work.
- Inspect worktree status and health
- Recover stuck or orphaned worktrees
- Validate worktree-to-main merge readiness
Worktree Commit-Merge-Push Flow
When handling a worktree branch:
cdinto the worktree directory- Run
git status— if there are uncommitted changes, stage and commit them - Return to main repo, merge the branch
- Push to remote
- Clean up worktree and branch
This is the ONLY correct flow. Never merge an empty worktree — if there are no commits beyond main, the agent's work was lost. Report this as an error.
5. Push Operations
- Push committed changes to remote after workflow completion
- Verify unpushed commits exist before push:
git log --oneline origin/main..HEAD - Execute push:
git push origin main - Verify push succeeded: confirm
git log --oneline origin/main..HEADreturns empty - Report push result in Operations Performed table
- NEVER use
--forcepush without explicit user confirmation
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.
- 5d ago Changed 25268a8d2c14
- 6d ago Changed · +1 lines 07823be49e3e
- 25d ago Changed · +3 lines cf2e56e8839a
- 26d ago Changed · +14 lines 94727c2d461d
- 1mo ago First seen · 171 lines · 43 tokens per session scan A fe4a1d5424f2
gitops is an agent published in the GitHub repository komluk/scaffolding (15 stars, last pushed yesterday), licensed MIT. It adds 43 tokens to every session and 2,979 once invoked, about $0.0002 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 2026-08-30.
Other agents, from other repositories
implementer
Implements ONE planned item in the isolated worktree, exactly one commit per item. Use after planner + navigator, and again on each gate/review loopback to fix only the reported findings.
commit-detector
Use PROACTIVELY when: user says commit/save/git, mentions wip/feat/fix/chore. Do NOT use for: code review, non-commit git ops (log/diff/status).
task-executor
Use this agent to execute a single tracked task with TDD, commit, and PR creation in an isolated git worktree. Dispatched by /coco:loop for parallel execution. Context: Multiple tasks are ready with non-overlapping file ownership. /coco:loop dispatches parallel agents. assistant: "I'll dispatch task-executor agents…
cad-assumptions-analyzer-high
The high rung of cad-assumptions-analyzer; bin/route.mjs picks it, not the user.
cad-plan-checker-high
The high rung of cad-plan-checker; bin/route.mjs picks it, not the user.
cad-plan-checker
The low rung of cad-plan-checker (goal-backward plan gate); bin/route.mjs picks it, not the user.