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 agentmods add skills/maxgfeller/open-harness/changesetnpx skills add MaxGfeller/open-harness --skill changesetgit clone --depth 1 https://github.com/MaxGfeller/open-harnessWrote 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/maxgfeller/open-harness/changeset)<a href="https://agentmods.dev/skills/maxgfeller/open-harness/changeset"><img src="https://agentmods.dev/badge/skills/maxgfeller/open-harness/changeset.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 | $0.00016 | $0.00327 |
| Opus 5 | $0.00008 | $0.00163 |
| Sonnet 5 | $0.00003 | $0.00065 |
| Haiku 4.5 | $0.00002 | $0.00033 |
Grade A, and why
changeset 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 4d 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.
What it actually says
Create or update a .changeset/*.md file for the current branch.
Repo-specific rules:
- Only publishable packages belong in a changeset:
@openharness/core,@openharness/provider-chatgpt,@openharness/provider-vfs,@openharness/react,@openharness/vue. - Ignore
apps/*andexamples/*unless they reveal a user-facing package behavior change that should still be described under one of the public packages. - If the branch only changes docs, examples, or website content, say that no changeset is needed instead of inventing one.
- Prefer the smallest valid bump. Use
majoronly for real breaking API or behavior changes. - Write notes for users, not implementation archaeology. One short paragraph is usually enough.
Workflow:
- Inspect staged changes first. If nothing is staged, compare the branch against
main. - Identify which public packages changed and choose the bump level for each package.
- If the bump is ambiguous, or if any package needs a
majorbump, stop and ask for confirmation before writing the file. - Write the changeset file in
.changeset/with frontmatter for the affected packages and a concise note below it. - Show the file contents after writing it.
If the user supplied extra context in the command arguments, incorporate it into the summary when it improves the release note.
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.
- 4d ago First seen · 27 lines · 16 tokens per session scan A 68432acf597c
changeset is a skill published in the GitHub repository MaxGfeller/open-harness (606 stars, last pushed 1mo ago), licensed MIT. It adds 16 tokens to every session and 327 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 2026-08-30.
Other skills, from other repositories
exit-strategy
Use when implementation is complete and all tests pass — guides the clean exit from a development branch with structured options for merge, PR, or cleanup.
project-release-maintainer
Project overlay for release and packaging maintenance across install layout, shipped assets, automation, license and notice alignment, and release docs. Not for content-only documentation or publishing without explicit authorization.
release
Bump the AgentSync version, write a CHANGELOG entry summarising changes since the last tag, and prepare a clean release commit. Use this skill when the user asks to release, ship, cut a version, bump major/minor/patch, tag, or prepare a new version — including phrasings like "let's ship 0.12", "bump the version"…
agent-framework-py-release
Use when cutting a Python release for the microsoft/agent-framework monorepo. Triggers on "bump py versions", "cut a python release", "prepare release PR for python", "release py packages", "bump python to X.Y.Z", or similar requests to bump Python package versions and prepare a release PR. Handles all four lifecycle…
hs-release
Cut a core Hindsight release (vX.Y.Z) and open the changelog + blog PR. Use when asked to cut/start a release, bump the version, or publish a new Hindsight version.
python-release
Handle Python SDK release, build, bump, packaging metadata, PyPI client pin, uv.lock, nox/build workflow, and publish verification changes. Use for Python release process work or dependency pin bumps; do not use for ordinary Python feature implementation.