T3 Code is an app for controlling AI coding agents running on a user's computer through mobile, web, and desktop interfaces. Developers use it to work remotely with supported agents such as Codex, Claude Code, Cursor, Grok Build, OpenCode, and Antigravity. The catalogue add-ons support the T3 Code workflow.
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 pingdotgg/t3code --skill changesetsgit clone --depth 1 https://github.com/pingdotgg/t3codeWrote 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/pingdotgg/t3code/changesets)<a href="https://agentmods.dev/skills/pingdotgg/t3code/changesets"><img src="https://agentmods.dev/badge/skills/pingdotgg/t3code/changesets/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/pingdotgg/t3code/changesets"><img src="https://agentmods.dev/badge/skills/pingdotgg/t3code/changesets.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 | $0.00042 | $0.00723 |
| Opus 5.5 | $0.00017 | $0.00289 |
| Sonnet 5.5 | $0.00008 | $0.00145 |
| Haiku 4.5 | $0.00004 | $0.00072 |
Grade A, and why
changesets 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 10d 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.
Copies of this mod
4 near-identical copies found in the catalogue:
- changesets — 100% identical, 35 lines differ
- changesets — 100% identical, 0 lines differ
- changesets — 100% identical, 35 lines differ
- changesets — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Treat a changeset as the release note for the complete PR, not as a log of work performed along the way. Finalize it after the current implementation scope and focused validation are complete.
Workflow
- Inspect the complete diff from the merge base, including changeset files already introduced by the PR, and identify directly affected published packages.
- Classify impact across source types, runtime behavior, entrypoints, required services, lifecycle, and persisted or wire data.
- Perform the breaking audit below.
- Record a reason no changeset is required, or update the PR's existing changeset. Create one only when the PR does not have one. When required, read authoring.md.
- Validate package names, frontmatter, bump policy, and a concise consumer-facing description.
Do not include unrelated worktree changes.
PR-level consolidation
The default is one changeset file per PR. One file can name several packages and summarize several related fixes or additions. Successive prompts, commits, and subtasks within the same PR update that file. If implementation resumes after a changeset was drafted, revise it during the next finalization pass.
Use separate files only when a maintainer requests the split or the PR contains independent changes that need separate release notes.
Requirement
Create a changeset for observable runtime behavior changes, including bug fixes; exported value or public type changes; entrypoint or export-map changes; changes to required services, errors, ownership, defaults, or lifecycle; and persisted, serialization, protocol, or wire-format changes.
Tests-only changes, behavior-preserving internal refactors, documentation or JSDoc maintenance, and unpublished tooling normally do not need one. When unclear, inspect exports and consumer-visible declarations rather than inferring from source location.
Breaking Audit
A change is breaking when valid existing consumer code, configuration, or data must change to keep compiling or behaving according to the previous contract. Audit every surface:
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.
- 10d ago Changed · +17 lines · -2 tokens per session c28b2a72be12
- 27d ago First seen · 59 lines · 44 tokens per session scan A 285aa88c9322
changesets is a skill published in the GitHub repository pingdotgg/t3code (27,790 stars, last pushed today), licensed MIT. It adds 42 tokens to every session and 723 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 2026-09-19.
Other skills, from other repositories
release-announcement
Write a release announcement — changelog, blog post, in-app note, or social post — that leads with user impact, names the audience, and includes upgrade/migration steps without filler.
release-notes
Generate user-facing release notes from tickets, PRDs, or changelogs. Creates clear, engaging summaries organized by category (new features, improvements, fixes). Use when writing release notes, creating changelogs, announcing product updates, or summarizing what shipped.
multi-agent-release-manager
Cleans up the workspace, formats code, runs presubmit checks, and uploads CLs to Gerrit.
release-helper
Ensures configuration and code changes are released correctly. Use PROACTIVELY whenever you edit config.json, change any setting, or fix a configuration bug in this project, so the change reaches production.
pack-submit
Package one of this agent's own skills as a standalone community pack and submit it to the aeon registry as a PR.
updater_guide
Guidance for checking for and installing Row-Bot updates.