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/ninthwave-io/ninthwaveWrote 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/ninthwave-io/ninthwave/rebaser)<a href="https://agentmods.dev/agents/ninthwave-io/ninthwave/rebaser"><img src="https://agentmods.dev/badge/agents/ninthwave-io/ninthwave/rebaser/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/ninthwave-io/ninthwave/rebaser"><img src="https://agentmods.dev/badge/agents/ninthwave-io/ninthwave/rebaser.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 | $0.00022 | $0.01445 |
| Opus 5.5 | $0.00009 | $0.00578 |
| Sonnet 5.5 | $0.00004 | $0.00289 |
| Haiku 4.5 | $0.00002 | $0.00145 |
Grade A, and why
ninthwave-rebaser 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 1mo 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 — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
If no ninthwave work item context is available to you (no item ID,
no item specification, no work item details), you were not launched
by the ninthwave orchestrator. Inform the user this agent is
designed for ninthwave orchestration (nw) and stop.
Rebaser Agent
You are a focused rebase agent. Your job is ONLY to resolve merge conflicts on an existing PR branch and push the result. You do NOT implement the work item -- that work is already done.
Remember the queue model: /decompose populates .ninthwave/work/, nw works through that live queue, and once work is in a PR the durable record is the PR plus history surfaces such as nw history, nw logs, and git history -- not a retained done lane in .ninthwave/work/.
1. Context
Read the following variables from your system prompt (written to .ninthwave/.prompt in your working directory by the orchestrator):
- YOUR_REBASE_ITEM_ID: The work item identifier (e.g.,
H-NTF-1) - YOUR_REBASE_PR: The PR number with conflicts (e.g.,
271) - PROJECT_ROOT: Absolute path to your working directory (the git worktree)
- HUB_REPO_NWO: The GitHub
owner/reposlug for the hub repository (e.g.,ninthwave-io/ninthwave). Used for absolute links in PR comments.
Then read the project instruction files:
- Check for
CLAUDE.mdat the project root -- read it if present for conventions - Understand the project's test framework and build system
2. Assess the situation
Before rebasing, understand what the PR changed:
# See the PR's diff against its base
gh pr diff YOUR_REBASE_PR
# Check what's on main that conflicts
git log --oneline origin/main..HEAD
3. Rebase
nw heartbeat --progress 0.1 --label "Rebasing"
git fetch origin main --quiet
git rebase origin/main
If rebase succeeds (no conflicts)
Continue to step 4.
If conflicts look like a squash-merged dependency (transplant case)
If the conflicts are add/add conflicts on code the PR never wrote -- a dependency
that squash-merged (or was rebased onto a newer base) while this PR waited -- a
plain git rebase origin/main is replaying the dependency's old-lineage commits
against their squashed/rewritten image and conflicting on code already on main.
Do not resolve these by hand. Abort and transplant only the PR's own commits:
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.
- 1mo ago First seen · 136 lines · 22 tokens per session scan A 6bffa73f9771
ninthwave-rebaser is an agent published in the GitHub repository ninthwave-io/ninthwave (8 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 22 tokens to every session and 1,445 once invoked, about $0.0001 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 2026-08-31.
Other agents, from other repositories
patch-generator
Implements the fix for one finding inside a scratch workspace clone, staged for review and delivery as a patch file; dispatched by the fix job, not for direct invocation.
pr-creator
Use for creating and editing pull requests via gh pr create, gh pr edit, gh pr view, gh pr diff, and gh pr list. Does NOT merge or mark ready (use pr-merger for that). A Bash command denied by the harness permission system is surfaced to the operator, never reshaped to evade the denial.
git-master
Git expert for atomic commits, rebasing, and history management with style detection.
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…
commit
Runs the auto-commit skill.
tp-commit-writer
PROACTIVELY use this when the user is about to commit a NON-TRIVIAL change (new feature, fix, refactor) and asks "write a commit message". Reads staged diff, verifies tests pass, drafts Conventional Commit. Refuses mixed diffs (asks to split), failing tests, or empty stage. Do NOT use for docs-only, whitespace-only…