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.
git clone --depth 1 https://github.com/rajconnects/founder-stackWrote 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/rajconnects/founder-stack/publish-gate)<a href="https://agentmods.dev/commands/rajconnects/founder-stack/publish-gate"><img src="https://agentmods.dev/badge/commands/rajconnects/founder-stack/publish-gate/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/rajconnects/founder-stack/publish-gate"><img src="https://agentmods.dev/badge/commands/rajconnects/founder-stack/publish-gate.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 | $0.00043 | $0.01034 |
| Opus 5.5 | $0.00017 | $0.00414 |
| Sonnet 5.5 | $0.00009 | $0.00207 |
| Haiku 4.5 | $0.00004 | $0.00103 |
Grade A, and why
publish-gate 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 1mo 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 — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are running the publish gate. This gate runs BEFORE the user runs npm publish (or equivalent). It validates that the artifact you're about to ship will actually work when a fresh consumer installs it.
Arguments: $ARGUMENTS
Why this gate exists
prepublishOnly runs unit tests against your local source tree. Unit tests do not catch:
- Files referenced from
package.json(bin, hooks, scripts) that are missing from thefilesallowlist → consumer install crashes withMODULE_NOT_FOUND. - Postinstall hooks that work in dev because the file lives in the working directory, but fail in install because the working directory is the npm cache.
- Build artifacts in
dist/that are stale because someone forgot to runnpm run buildbefore publishing. - Any "works on my machine" gap between the dev checkout and the tarball.
This gate closes that gap by installing the actual tarball and running it as a fresh consumer.
Steps
-
Read
.claude/project.json. Extract therelease_artifactsarray. If absent or empty, fail fast: "publish-gate requiresrelease_artifactsin project.json. Skip this gate if the project doesn't ship a packaged artifact." -
Filter to scope. If
$ARGUMENTSis empty, run all artifacts. Otherwise, run only the artifact whosenamematches$ARGUMENTS. If no match, list available names and fail. -
For each artifact, in sequence:
a.
cdintopath(the artifact's source root, e.g.apps/<package-name>).b. Pack. Run
npm pack --pack-destination /tmp/<artifact-name>-pack(or the equivalent for the artifacttype:npm→npm pack,docker→docker build,python→python -m build). Capture the output file path.c. Install into a fresh tmpdir.
mktemp -d→cdinto it → install the local tarball (npm install <tarball-path>or equivalent). Fornpm, use--prefix .to keep the install local to the tmpdir, so this gate never touches the user's global modules.d. Run the smoke command. Execute
smoke(the field on the artifact entry — e.g.<package-name> --versionor<package-name> doctor) from inside the tmpdir, with the localnode_modules/.binon PATH if needed.
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.
- 1mo ago First seen · 54 lines · 43 tokens per session scan A 8791b2fdf573
publish-gate is a command published in the GitHub repository rajconnects/founder-stack (3 stars, last pushed 3mo ago), licensed MIT. It adds 43 tokens to every session and 1,034 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 2026-08-31.
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.
qa-ship
Run Phase 5 QA validation, acceptance testing, and release preparation.