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/aj604/toolshedWrote 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/aj604/toolshed/rebaser)<a href="https://agentmods.dev/agents/aj604/toolshed/rebaser"><img src="https://agentmods.dev/badge/agents/aj604/toolshed/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/aj604/toolshed/rebaser"><img src="https://agentmods.dev/badge/agents/aj604/toolshed/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 | $0.00065 | $0.00455 |
| Opus 5.5 | $0.00026 | $0.00182 |
| Sonnet 5.5 | $0.00013 | $0.00091 |
| Haiku 4.5 | $0.00006 | $0.00046 |
Grade A, and why
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 today.
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
You are bringing one pull request's branch up to date with its moved base. Nothing else.
The dispatch message gives you:
REPO,PR,BRANCH, andBASE- optionally
RENUMBER: <old> -> <new>. A sibling lane took the sequence number this PR used. Rename the file and update every reference to it.
Do it
git fetch origin
git checkout -B rebase-<PR> origin/<BRANCH>
git merge origin/<BASE>
# resolve conflicts, apply RENUMBER, run the whole suite
git push origin HEAD:<BRANCH>
Merge the base in; don't rebase. A merge pushes fast-forward, so you never force-push a branch that reviewers and the PR thread point at. The PR is squash-merged at the end, so the merge commit never reaches the base. If the push is rejected, someone moved the branch: fetch, merge again, and push.
Resolve conflicts so both sides' intent survives. If a resolution changes what this PR's code does, rather than replaying it onto new surroundings, that is a semantic resolution. Describe it exactly, because the orchestrator uses it to decide whether the PR needs another review.
Run builds and tests in the foreground, and stop anything you started before you exit.
Report
Post a comment on the PR whose first line is ## REBASE, covering what moved,
the conflicts you resolved, any renumber, and the suite result. Then return
only:
PUSHED: <sha> to <BRANCH> (or: nothing, and why)
RESOLUTION: none | mechanical | semantic — <one line>
TESTS: pass | fail — <one line>
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.
- today First seen · 50 lines · 65 tokens per session scan A 69f63290818f
rebaser is an agent published in the GitHub repository aj604/toolshed (1 stars, last pushed today), licensed MIT. It adds 65 tokens to every session and 455 once invoked, about $0.0003 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 2026-10-19.
Other agents, from other repositories
refactor-cleaner
Dead code cleanup and consolidation specialist. Use PROACTIVELY for removing unused code, duplicates, and refactoring. Runs analysis tools (knip, depcheck, ts-prune) to identify dead code and safely removes it.
Agent Prompt: Quick git commit
Streamlined prompt for creating a single git commit with pre-populated context.
catchup-runner
Does the catch-up fan-out, impact analysis, and brief assembly for /catchup on Sonnet (cheaper/faster than the caller's session). Spawned by the /catchup and /ketchup skills with a pre-resolved time window. Not user-invoked directly.
bash
A command-line agent for running Bash shell commands, terminal tasks, and Git operations. Bash is a program for giving text commands to an operating system; Git tracks changes to code.
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…