Borrowing it
Nothing to install: this file belongs to Osiris-DevWorks/smart-citizen. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Osiris-DevWorks/smart-citizen/main/.claude/commands/PRE_RELEASE.mdgit clone --depth 1 https://github.com/Osiris-DevWorks/smart-citizenWrote 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/commands/osiris-devworks/smart-citizen/pre_release)<a href="https://agentmods.dev/commands/osiris-devworks/smart-citizen/pre_release"><img src="https://agentmods.dev/badge/commands/osiris-devworks/smart-citizen/pre_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/commands/osiris-devworks/smart-citizen/pre_release"><img src="https://agentmods.dev/badge/commands/osiris-devworks/smart-citizen/pre_release.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 | $0.00054 | $0.03795 |
| Opus 5.5 | $0.00022 | $0.01518 |
| Sonnet 5.5 | $0.00011 | $0.00759 |
| Haiku 4.5 | $0.00005 | $0.00380 |
Grade A, and why
PRE_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 2mo 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 — 241 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/pre_release
Run before merging the active release/X.Y.Z integration branch to main. This is the final gate before the release ships — it confirms code quality, doc currency, test coverage, that every activated language covers the release's user-facing strings and docs, that the tester Test Plan reflects this release's scope, that every code contributor is acknowledged in the project's in-app About and the README, that frequent issue reporters are recognized as testers, and that every issue fixed this cycle is closed (when tester-verified) or explicitly held.
Work through every step in order. After each step, stop at the CHECKPOINT and wait for the user before continuing.
Preflight
- Confirm the current branch is
release/X.Y.Z. If not, abort and ask the user to switch. - Confirm working tree is clean (
git status --porcelain). If dirty, abort. - Confirm
VERSION.TXTmatchesX.Y.Z. If mismatched, surface the discrepancy and ask the user before proceeding.
CHECKPOINT — preflight confirms release branch is ready for audit. Proceed? Wait for the user.
1. Test coverage check
Follow the procedure in .claude/commands/test_coverage_check.md. Present findings grouped by severity (Critical / Major / Minor) and end with the verdict line.
CHECKPOINT — ready for the next check? Wait for the user.
2. UI / docs / tutorial sync check
Follow the procedure in .claude/commands/docs_sync_check.md. Present findings grouped by severity and end with the verdict line.
CHECKPOINT — ready for the next check? Wait for the user.
3. Language support check
Follow the procedure in .claude/commands/language_support_check.md. Present findings grouped by severity and end with the verdict line.
This is the pre-release docs-sync moment the translation policy points at: with the user's approval at this step's checkpoint, AI backfill of missing translations is in scope here (fill at only, never touch a non-empty ht, record the work per languages/TRANSLATIONS.md). New strings that landed this cycle in english/ui.json only are exactly what this step exists to catch.
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.
- 2mo ago First seen · 241 lines · 54 tokens per session scan A 61c5c2902507
PRE_RELEASE is a command published in the GitHub repository Osiris-DevWorks/smart-citizen (114 stars, last pushed today), licensed Apache-2.0. It adds 54 tokens to every session and 3,795 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 2026-08-30.
Other commands, from other repositories
speckit.spex.finish
Smoke test + squash + merge/keep (land the code on main).
wg-release
Manage versions and generate changelogs for the wicked-garden plugin.
4-close-project
Name: 4-close-project Purpose: Apply an OpenSpec change through TDD, verify it, prepare or update the PR, and leave archive for after merge.
release-check
Run the release-readiness umbrella + draft a tweet-length announcement.
explore-release
This legacy command is a rename notice only. Its workflow is now rpi-explore-release.
publish-gate
Pre-publish smoke verification — pack, install into a tmpdir, run the configured smoke command, assert expected output. Catches the "code worked locally but the published tarball is broken" class of bug.