PrimeIntellect-ai/verifiers is a library for building environments that train and evaluate large language models. It is used with the Environments Hub, the prime-rl training framework, and Prime Intellect’s Hosted Training platform. Its catalogue add-ons provide coding-agent instructions and skills for working with the library.
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 PrimeIntellect-ai/verifiers --skill releasegit clone --depth 1 https://github.com/PrimeIntellect-ai/verifiersWrote 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/primeintellect-ai/verifiers/release)<a href="https://agentmods.dev/skills/primeintellect-ai/verifiers/release"><img src="https://agentmods.dev/badge/skills/primeintellect-ai/verifiers/release/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/primeintellect-ai/verifiers/release"><img src="https://agentmods.dev/badge/skills/primeintellect-ai/verifiers/release.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 | $0.00017 | $0.00434 |
| Opus 5.5 | $0.00007 | $0.00174 |
| Sonnet 5.5 | $0.00003 | $0.00087 |
| Haiku 4.5 | $0.00002 | $0.00043 |
Grade A, and why
release 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 2d 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
Release Verifiers
By default, bump to the next minor vX.Y.Z version unless the user specifies a different target version, and only run the release steps the user has authorized.
1. Prepare main
Run the release from a clean checkout of main:
git switch main
git pull --ff-only origin main
git status --short --branch
VERSION=vX.Y.Z
Confirm that the worktree has no local changes and that $VERSION has not already been published to GitHub or PyPI. Check pyproject.toml to verify all dependencies are pinned to published stable versions. If any use .dev, alpha, beta, or release-candidate versions, update them with uv (so uv.lock updates too), land the change through a normal PR, and pull main again before tagging.
2. Tag latest main
git tag "$VERSION"
git push origin "refs/tags/$VERSION"
Confirm that the remote tag points to the current main commit.
3. Publish
Manually dispatch the stable release workflow:
gh workflow run publish.yml \
--repo PrimeIntellect-ai/verifiers \
--ref main \
-f tag="$VERSION"
Watch the workflow run to completion with gh run watch <run-id> --exit-status.
4. Update the release notes
Once the workflow creates the public GitHub Release, summarize the changes since the previous stable release using the same release-note format, then update the new release:
gh release edit "$VERSION" \
--repo PrimeIntellect-ai/verifiers \
--notes-file <release-notes.md>
5. Verify
Confirm that:
- PyPI lists
${VERSION#v}with both a wheel and a source archive. - The GitHub Release is public with both files attached.
- The release notes match the format of prior releases.
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.
- 2d ago Changed · -8 lines 9de0ee500806
- 4d ago Changed 8f74740ea569
- 1mo ago First seen · 70 lines · 17 tokens per session scan A 626ccab42ecb
release is a skill published in the GitHub repository PrimeIntellect-ai/verifiers (4,717 stars, last pushed today), licensed MIT. It adds 17 tokens to every session and 434 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
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.
release
Fully automate a release with version-bump and childhood.
multi-agent-release-manager
Cleans up the workspace, formats code, runs presubmit checks, and uploads CLs to Gerrit.
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.
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.