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/rajdeepratan/SlashForgeWrote 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/rajdeepratan/slashforge/cut-release)<a href="https://agentmods.dev/commands/rajdeepratan/slashforge/cut-release"><img src="https://agentmods.dev/badge/commands/rajdeepratan/slashforge/cut-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/rajdeepratan/slashforge/cut-release"><img src="https://agentmods.dev/badge/commands/rajdeepratan/slashforge/cut-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 | $0.00025 | $0.00543 |
| Opus 5.5 | $0.00010 | $0.00217 |
| Sonnet 5.5 | $0.00005 | $0.00109 |
| Haiku 4.5 | $0.00003 | $0.00054 |
Grade A, and why
cut-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 7d 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
Cut a release of slashforge. The version bump is the publish trigger: merging a
package.json version change to main runs .github/workflows/auto-release.yml
(creates the GitHub release tag), which runs .github/workflows/publish.yml
(tests, then OIDC trusted-publish to npm — no token). So treat this as a
deliberate, human-gated action.
Argument $ARGUMENTS is the bump (major / minor / patch) or an explicit
version. If absent, ask.
Steps
- Confirm the tree is green and clean. Run
npm testandgit status. Do not proceed on a red or dirty tree. - Confirm the current and target version with the user before changing anything — read the current version from
package.json. - Finalize
CHANGELOG.md. Move everything under## [Unreleased]into a new dated section for the target version (Keep a Changelog format). Leave a fresh empty## [Unreleased]. - Bump the version in
package.jsonto the target. Do this on arelease/<version>branch — never commit the bump directly tomain. - Open a PR targeting
main(ask who reviews). The PR body lists the changelog entries for this version. - Explain the publish chain to the user and stop: on merge, auto-release creates the tag and publish.yml publishes to npm via OIDC. If publish fails with an EOTP/2FA error, it means a
NODE_AUTH_TOKENis set and overriding OIDC — it must be absent for trusted publishing to work.
Verify
-
npm testgreen and tree clean before bumping - Target version confirmed with the user
-
CHANGELOG.mdhas a dated section for this version and a fresh empty## [Unreleased] - Version bump is on a
release/<version>branch, notmain - PR opened against
mainwith reviewers assigned - User understands the merge publishes automatically
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.
- 7d ago First seen · 36 lines · 25 tokens per session scan A e5c9e698d899
cut-release is a command published in the GitHub repository rajdeepratan/SlashForge (5 stars, last pushed 2d ago), licensed MIT. It adds 25 tokens to every session and 543 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 2026-10-09.
Other commands, from other repositories
land
Resolve and squash merge one named, currently authorized pull request.
resolve-pr
Resolve PR review feedback — fetch unresolved threads, triage, dispatch resolver agents, reply + resolve via GraphQL.
release
Release manager for frontend and mobile. Writes App Store notes, user-facing changelog, flags stale docs and landing copy. Actions: notes | changelog | docs | sync.
sweep-mode-c-lifecycle
If Mode C was selected, the wave lifecycle is the back half of the issue-side lifecycle: no Curator, no Approval gate, no Builder. Each PR is routed by its current label to Judge, Doctor→Judge, or Merge directly.
merge
Finish a PR properly: every check green, every review addressed — human and bot — then merge and clean up.
pr
Prepare and open a pull request the senior way: gate, template, scrubbed, everything visible.