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 theonedev/tod --skill submit-pull-request-workgit clone --depth 1 https://github.com/theonedev/todWrote 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/theonedev/tod/submit-pull-request-work)<a href="https://agentmods.dev/skills/theonedev/tod/submit-pull-request-work"><img src="https://agentmods.dev/badge/skills/theonedev/tod/submit-pull-request-work/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/theonedev/tod/submit-pull-request-work"><img src="https://agentmods.dev/badge/skills/theonedev/tod/submit-pull-request-work.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 | $0.00032 | $0.02186 |
| Opus 5.5 | $0.00013 | $0.00874 |
| Sonnet 5.5 | $0.00006 | $0.00437 |
| Haiku 4.5 | $0.00003 | $0.00219 |
Grade A, and why
submit-pull-request-work 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 — 212 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Submit pull request work
Submit code changes and/or saved comments for an existing pull request. This workflow does not create a pull request.
Prerequisites
todis installed and configured.- The current repository belongs to the PR's source or target project.
Session handoff
This workflow pairs with work-on-pull-request. At the start, recover
<saved-pr-actions> from the same chat session:
- From a prior
work-on-pull-requestrun -- use the exact drafted actions presented or amended earlier in this session, including comment text and parameters (comment-id, file, line range, approve/request-changes, merge, etc.). - From the user's submit prompt -- if the user supplies or revises actions
when asking to submit, treat that as
<saved-pr-actions>. - Otherwise --
<saved-pr-actions>is empty.
<saved-pr-actions> is session state, not a file on disk and not discussion
already on OneDev. Step 5 applies these deferred drafts.
Before counting or applying actions, discard text-posting actions with empty or whitespace-only content, and omit blank optional notes or summaries. An empty handoff has zero actions.
Aborting the workflow
Run the workflow sequentially. Before aborting it for any reason, always follow
this section. If the current user is an AI user and <pr-reference> is known,
immediately run
tod pr add-comment <pr-reference> '<reason>' to explain the stop reason.
Report the reason, including the command and error when applicable, and stop.
Interactive questions
If the current user is an AI user, do not ask the current user for direction in this workflow. When you would otherwise ask a question, post a concise PR comment explaining the blocker or needed decision, then stop:
tod pr add-comment <pr-reference> '<reason>'
Shell quoting for authored text
When passing authored text such as Markdown comments, review notes, summaries,
or commit messages to tod from a shell command, quote it so the shell
preserves it literally. Prefer a single-quoted argument, and escape any literal
single quote inside the text as '\''. Do not wrap text containing backticks in
double quotes, as the shell will treat backticks as command substitution before
tod receives the text.
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 · +4 lines 1db1729073c1
- 1mo ago Changed 30d1b101b368
- 1mo ago First seen · 208 lines · 32 tokens per session scan A 0bc5beeee0fb
submit-pull-request-work is a skill published in the GitHub repository theonedev/tod (15 stars, last pushed 6d ago), licensed MIT. It adds 32 tokens to every session and 2,186 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 2026-08-30.
Other skills, from other repositories
review-implement-phase
Implements triaged review actions, commits focused fixes, and posts Done plus resolves threads. Use when the user wants only the implementation phase of the review-framework workflow.
pr
Draft a PR body from OMC's paper trail — the smallest visual that proves the change, evidence consumed from the verify protocol (never re-collected), reversibility from the ADR test on the diff, glossary language throughout.
merge-batch
Prepare and merge an owner-selected PR batch with contributor credit and exact-candidate admission. Use for a pasted PR list; combined focused validation is diagnostic, and every actual landing still requires its applicable checks and authorization.
otto-pr-review-loop
Run Polly and OCR on a PR until all findings settle.
engram-branch-pr
PR creation workflow for Engram following the issue-first enforcement system. Trigger: When creating a pull request, opening a PR, or preparing changes for review.
verify-behavior
Verify or reproduce visible product behavior by driving the real UI with pi-computer-use's checked tools, requiring verified expect postconditions and durable state evidence for meaningful UI flows. Use when triage needs visual reproduction, implementation needs behavioral proof, review needs interactive confirmation…