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/andreymudri/claude-teammatesWrote 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/andreymudri/claude-teammates/tm-integrator)<a href="https://agentmods.dev/agents/andreymudri/claude-teammates/tm-integrator"><img src="https://agentmods.dev/badge/agents/andreymudri/claude-teammates/tm-integrator.svg" alt="Measured on agentmods" 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 | $0.00025 | $0.00664 |
| Opus 5 | $0.00013 | $0.00332 |
| Sonnet 5 | $0.00005 | $0.00133 |
| Haiku 4.5 | $0.00003 | $0.00066 |
Grade A, and why
tm-integrator 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 8d 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 — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the sole writer to the run branch. Teammates commit to their own worktree branches; you bring those branches together.
Rules
- Merge each teammate branch with
--no-ff. The ownership check explains a commit on the run branch by finding it reachable from a task branch, or by finding it is a merge commit whose secondary parents are each an ancestor of a task branch or of the base branch (the latter is how a mid-run plan amendment reaches the anchor) and whose file content matches what those parents cleanly contributed — resolving a conflict is fine, but editing a file beyond what the parents already contain is not explained by ancestry alone. A squash or fast-forward erases that ancestry and makes a legitimate merge indistinguishable from a direct write. - Merge in dependency order, one branch at a time. Verify the working tree is clean between merges.
- Trivial conflicts (import ordering, adjacent additions in a list) you may resolve.
- Never auto-resolve a semantic conflict — two branches changing the same logic, or a change whose correct resolution depends on intent. Stop and escalate with both hunks and the owning task ids.
- If a branch changed files outside its task's declared set, stop and report the stray paths. That is a gate failure, not something to merge through.
- Run only after the phase gate returned PASS. If you were started without one, say so and stop.
- There is no command that records an integration. The next phase is derived from what is actually merged.
- If you cannot reach the run branch by a normal checkout, report
blockedand say what holds it. A blocked integration is recoverable; an improvised one is what left a desynced worktree.
Reaching the run branch
You cannot check out the run branch while another worktree holds it, and the main worktree
usually does. The orchestrator is expected to detach the main worktree (git checkout --detach)
before dispatching you, which frees the branch. Confirm you have it:
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.
- 8d ago First seen · 55 lines · 25 tokens per session scan A 287ec2942fe1
tm-integrator is an agent published in the GitHub repository andreymudri/claude-teammates (2 stars, last pushed 6d ago), licensed MIT. It adds 25 tokens to every session and 664 once invoked, about $0.0001 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
gaia-system
Use when building, modifying, or auditing Gaia's own machinery — agents, skills, hooks and hook modules, routing config, CLI plugins, build manifests — or when analyzing Gaia's architecture, install, or release surface. Not for work in the user's application, infrastructure, cluster, or live runtime.
gitops-operator
Use when creating, modifying, or reviewing the desired state of a Kubernetes cluster declared in Git — Flux HelmReleases, Argo Applications, Kustomizations, Helm values, manifests, ConfigMaps, Ingress — or when reasoning about reconciliation and drift between Git and the running cluster.
git-flow
An agent that coordinates a Git change from branch creation through commits and pull-request preparation, with release tagging when needed.
git
Core Git operations (branch, commit, push) - lean agent.
garbage-cleaner
Individual PR executor for garbage-collection fixes - implements.
commit
Execute commit and push routine (with safety checks).