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 jcarlosrodicio/opencode-agent-orchestration-kit --skill oak-commitgit clone --depth 1 https://github.com/jcarlosrodicio/opencode-agent-orchestration-kitWrote 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/jcarlosrodicio/opencode-agent-orchestration-kit/oak-commit)<a href="https://agentmods.dev/skills/jcarlosrodicio/opencode-agent-orchestration-kit/oak-commit"><img src="https://agentmods.dev/badge/skills/jcarlosrodicio/opencode-agent-orchestration-kit/oak-commit/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/jcarlosrodicio/opencode-agent-orchestration-kit/oak-commit"><img src="https://agentmods.dev/badge/skills/jcarlosrodicio/opencode-agent-orchestration-kit/oak-commit.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 | $0.00047 | $0.00634 |
| Opus 5.5 | $0.00019 | $0.00254 |
| Sonnet 5.5 | $0.00009 | $0.00127 |
| Haiku 4.5 | $0.00005 | $0.00063 |
Grade A, and why
oak-commit 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 17d 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 — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Commit
When it runs
Outside /autonomous, commit only when the human asks for it. Under
/autonomous, this skill runs at delivery.
Pushing a branch and opening a pull request happen only through
oak deliver. Never run git push or gh pr create yourself.
Branch
Work on a feature branch that follows the repository's naming convention, never
on the default branch. If the repository has no convention, ask. Under
/autonomous, use <type>/<slug> and record that decision in the autonomy log.
Stage
- Run
git statusfirst. - Stage explicit paths only. Never use
git add -A,git add .,git add -uorgit commit -a. - List any unrelated change you see, and leave it unstaged. Never stash, revert or overwrite someone else's work.
- Read the staged diff (
git diff --cached) and check it for secrets, tokens,.envvalues and absolute machine paths before committing.
Commit
- One logical change per commit.
- English, imperative mood. Subject line
<type>: <summary>under 72 characters, where type is one offeat,fix,refactor,test,docs,choreorperf. - The body explains why first, then anything a later reader needs to know.
- Write the message from the staged diff only, not from memory of the session.
- Never claim that tests pass unless they ran in this session.
- Never bypass hooks (
--no-verify,-n). If a hook fails, fix the cause. - Keep option-like words such as
-n,-a,--allor--out of a-mmessage, and do not end it with.: the developer's shell rules deny them as hook bypass or bulk staging.
Pull-request body
Use these sections:
- What: the change, in one paragraph.
- Why: the problem it solves.
- How: the approach and the decisions that shaped it.
- Verification: the commands actually run, and what was not covered.
- Risk: what could break, and how to roll it back.
Refer to task artifacts and reports by their full repository path in
backticks instead of copying them into the body; relative Markdown links do not
resolve in a pull-request body. Write the
body to a file and pass it to oak deliver.
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.
- 17d ago First seen · 70 lines · 47 tokens per session scan A 2e4d995eada8
oak-commit is a skill published in the GitHub repository jcarlosrodicio/opencode-agent-orchestration-kit (133 stars, last pushed 18d ago), licensed Apache-2.0. It adds 47 tokens to every session and 634 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 2026-09-29.
Other skills, from other repositories
oma-scm
Manage Git branches, merges, conflicts, commits, and release baselines. Use for repository history and change-management operations.
git-commit
A guided Git commit workflow that examines changes and creates a commit message using the Conventional Commits format, a shared style for labeling changes such as features, fixes, tests, or documentation.
release
Cut and publish a full stable NAC release after main, release-PR, and publication CI pass. Use when a maintainer asks for a stable version bump, tag, or GitHub Release. Never use for release candidates; NAC RC releases are automated.
gentle-ai-work-unit-commits
Plan commits as reviewable work units. Trigger: implementation, commit splitting, chained PRs, or keeping tests and docs with code.
cmux-testing
Choose scoped cmux verification, add behavioral tests, and validate Swift test targets and wiring. Use when adding tests or deciding what local/CI evidence a change needs.
at-daily-log
Summarize each day's Git activity into a concise daily work log, for a single date or a range. Uses the current repository, optional configured work projects, or paths named in conversation; configuration is never required.