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/promptpartner/agentsmith/release-checknpx skills add PromptPartner/agentsmith --skill release-checkgit clone --depth 1 https://github.com/PromptPartner/agentsmithWrote 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/promptpartner/agentsmith/release-check)<a href="https://agentmods.dev/skills/promptpartner/agentsmith/release-check"><img src="https://agentmods.dev/badge/skills/promptpartner/agentsmith/release-check.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 | $0.00043 | $0.00558 |
| Opus 5 | $0.00022 | $0.00279 |
| Sonnet 5 | $0.00009 | $0.00112 |
| Haiku 4.5 | $0.00004 | $0.00056 |
Grade A, and why
release-check 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.
How it starts
The opening of the file, as written. The whole thing — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Release Check — Orchard
Cutting a release for Orchard is mechanical but easy to half-do (tag without the migration check, bump the version but forget the changelog). This skill is the checklist so nothing slips. It loads only when you're releasing — everyday work doesn't pay for it.
When this fires
You type /release-check, or you're about to tag a new Orchard version.
Checklist
Walk these in order. Stop at the first failure, fix it, restart — a release is atomic.
- Clean tree, right branch.
git statusis clean and you're onmain(or the release branch). No uncommitted work rides along in a tag. - Bump the version. Update
versioninpyproject.toml. Use semver: breaking API/contract change → major; new endpoint/field → minor; fix only → patch. - Migrations present and current.
alembic checkis clean (no model-vs-history drift), and every new revision has been applied once against a dump of representative data, not just an empty DB.alembic checkproves agreement, not applicability — this step proves applicability. - Verify is green. Run
scripts/verify.shand read the output:format,lint,types,migrations,testall pass. Within-a-layer green only — also confirm one real request path (TestClient against the full app) still works end to end. - Changelog updated. Add a dated section to
CHANGELOG.mdfor this version: what changed, and call out any API-contract or migration change explicitly so callers know to look. - Commit, then tag.
chore(release): vX.Y.Zcommit, thengit tag vX.Y.Z. Tag points at the release commit — never an earlier one. - Push commit and tag.
git push && git push --tags. Open/reference the GitHub release.
Notes
- If
alembic checkfails, you have a model change with no migration — that's a code bug, not a release step. Go back and add the revision before tagging. - Don't allowlist a secret to make a hook pass; the no-secrets rule is absolute (core).
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 · 41 lines · 43 tokens per session scan A 918facc4f6fe
release-check is a skill published in the GitHub repository PromptPartner/agentsmith (185 stars, last pushed today), licensed MIT. It adds 43 tokens to every session and 558 once invoked, about $0.0002 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
crit-cli
Use when an agent needs to author or reply to crit inline comments programmatically (including multi-agent workflows commenting on shared code/plans/docs/proposals), publish or unpublish a crit review with crit share, sync a crit review to or from a GitHub PR or GitLab MR, or read/interpret a crit review JSON file.…
crit
Review code changes, a plan, a live page (running dev server), or a local HTML file with Crit inline comments and structured human feedback. Use only when the user explicitly invokes /crit or directly asks to use Crit; a generic review request does not count.
crit-story
Author a crit story only when the user explicitly invokes /crit-story or directly asks you to generate a crit story. Do not infer this skill from generic review, PR, or diff-review requests.
truthmark-sync
Use automatically at finish-time after functional code changes, or explicit /truthmark-sync, $truthmark-sync, or /truthmark:sync. Skip docs-only, formatting-only, behavior-preserving renames, missing config, and no-code changes. Not for doc-first realization or manual topology design.
truthmark-document
Use when the user asks to document existing implemented behavior, or Sync, Check, or Structure finds implemented behavior missing canonical truth. Not for functional-code changes, doc-first implementation, or topology repair that needs Structure.
truthmark-realize
Use when the user explicitly asks to realize Truthmark truth docs into code, including /truthmark-realize, $truthmark-realize, or /truthmark:realize. Not for syncing docs after code changes, documenting existing code, topology repair, or truth audits.