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 skills add dylanroscover/Embody --skill merge-divergent-toxgit clone --depth 1 https://github.com/dylanroscover/EmbodyWrote 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/skills/dylanroscover/embody/merge-divergent-tox)<a href="https://agentmods.dev/skills/dylanroscover/embody/merge-divergent-tox"><img src="https://agentmods.dev/badge/skills/dylanroscover/embody/merge-divergent-tox/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/skills/dylanroscover/embody/merge-divergent-tox"><img src="https://agentmods.dev/badge/skills/dylanroscover/embody/merge-divergent-tox.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00074 | $0.01274 |
| Opus 5.5 | $0.00030 | $0.00510 |
| Sonnet 5.5 | $0.00015 | $0.00255 |
| Haiku 4.5 | $0.00007 | $0.00127 |
Grade A, and why
merge-divergent-tox 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 — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Merging Divergent .tox / .toe Binaries
Git cannot three-way-merge a .tox. It reports a conflict and offers you "ours or theirs", a choice that silently discards one side's work. This skill turns the binary into a reviewable text diff. Phases 0 to 2 need no TouchDesigner at all and carry no risk; in practice they often answer the whole question, so do not skip them to get to the interesting part. The commands for Phases 1 to 5 live in references/procedure.md in this skill's folder (get_guidance(topic='merge-divergent-tox/procedure') without a skills folder).
The rule that governs everything here
This is a THREE-way merge, not a two-way one. Both sides changed the file from a common ancestor. If you compare only ours against theirs, a difference tells you nothing about who moved: an operator present in theirs and absent in ours may be their addition or our deletion, and those demand opposite actions. Always diff each side against the BASE.
Phase 0: triage (no tools)
- Enumerate every conflicting binary, not just the ones you were asked about.
git diff --name-only --diff-filter=Ufor the active conflicts,git diff --stat <base>..<theirs> -- '*.tox' '*.toe'for everything that diverged. The file nobody mentioned is the one that breaks later. - Find the true per-file content base.
git merge-baseis often wrong: history rewrites and re-committed blobs move it. Verify per file; if the history was rewritten, compare commit SUBJECTS rather than SHAs to find which commits are genuinely absent. - Answer the product questions BEFORE opening TouchDesigner. If one side deleted a subsystem the other side extended, that is a product decision, not a merge decision. Resolving it can collapse the hardest files to "take ours" and end the job. Ask the human. This is the highest-leverage step in the skill and it costs nothing.
The phases and their gates
| Phase | What | The gate |
|---|---|---|
| 1 Extract | git cat-file blob all three sides into ours/, theirs/, base/ from Bash, never PowerShell |
Size equals the on-disk blob and the header reads 0000 0001 3130, or ABORT: a filter mangled the bytes |
| 2 Inventory | toeexpand.exe (works on .tox) each side to an ASCII tree, comm the operator lists against BASE, grep .parm/.cparm for values |
Judge by whether the .dir appeared, never by the exit code (it returns 1 on success). Most merges end here |
| 3 Sandbox | Only if Phase 2 left real work. A purpose-made empty .toe outside every live git root, its own git init, its own port; create the host COMP, allowCooking = False, THEN loadTox, in one call |
Never in a production project: extensions run at instantiation, before any hook, and Safe Mode does not stop that |
| 4 Export and diff | export_network(embed_all=True, include_dat_content=True) both sides |
embed_all is mandatory; export one side twice first to learn the format-noise floor |
| 5 Apply | Classify every difference against BASE (theirs-added, ours-added, both-changed, convergent), apply into ours, re-export, re-diff until only intended differences remain | COMP.save(), reload, diff once more: the round-trip gate |
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 Changed · -178 lines d03e4d930c06
- 1mo ago Changed eb9060e54050
- 1mo ago First seen · 231 lines · 74 tokens per session scan A d1e6dc79b0fc
merge-divergent-tox is a skill published in the GitHub repository dylanroscover/Embody (209 stars, last pushed yesterday), licensed MIT. It adds 74 tokens to every session and 1,274 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 2026-08-30.
Other skills, from other repositories
python-api
This skill should be used when writing, editing, or debugging Python code that runs inside TouchDesigner — scripts, expressions, DAT callbacks, Extensions, or one-off snippets passed to executepythonscript — or whenever there is uncertainty about a td class's methods, members, or module-level API. Trigger phrases…
git-workflow
Branching and review conventions.
git-workflow
Follow this team's Git conventions for branching, commit messages, and pull requests.
servicenow-studio-gitlab-app
Wire a ServiceNow scoped app (App Engine Studio / Fluent) to a GitLab repository and drive its promotion two ways — Path A: native Studio source control (servicenowsourcecontrol → importrepository / applyremotesourcecontrolchanges, handing off to servicenowcicd for publish/install), or Path B: GitLab-CI-driven…
gitlab-merge-request-review
Review and merge GitLab merge requests via the gitlab-api MCP server — by default the MRs assigned to you or where you are a reviewer, optionally scoped to a project, group, or the whole instance. Read an MR, gate it on a green pipeline (pipeline → jobs → job log), then approve, accept/merge, or set…
gitlab-merge-request-create
Open a new GitLab merge request against a project via the gitlab-api MCP server — from a source branch into a target branch, with title, description, assignees, reviewers, labels, and remove-source-branch/squash options. Use when the agent must create/open an MR for a project. Do NOT use to review, approve, or merge…