Borrowing it
Nothing to install: this file belongs to hyperlogue/r3. 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/hyperlogue/r3/main/.claude/skills/release/SKILL.mdgit clone --depth 1 https://github.com/hyperlogue/r3Wrote 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/hyperlogue/r3/release)<a href="https://agentmods.dev/skills/hyperlogue/r3/release"><img src="https://agentmods.dev/badge/skills/hyperlogue/r3/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/hyperlogue/r3/release"><img src="https://agentmods.dev/badge/skills/hyperlogue/r3/release.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Tool Misuse · line 99 Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
- medium Data Exfiltration · line 107 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
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 | $0.00081 | $0.02093 |
| Opus 5.5 | $0.00032 | $0.00837 |
| Sonnet 5.5 | $0.00016 | $0.00419 |
| Haiku 4.5 | $0.00008 | $0.00209 |
Grade A, and why
release scanned grade A with 1 finding 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 8d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
1. The GitHub Release (curl / Homebrew). Its description is the `## [X.Y.Z]` How it starts
The opening of the file, as written. The whole thing — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Releasing r3
A release is one version-bump commit plus an annotated tag on it. The whole job
is: write the changelog, move every version string to the new number
together, commit, and tag that commit. Push remains a separate user action.
The release CI reads CHANGELOG.md out of the tagged tree for the GitHub release notes, so the
changelog entry is the release's public face and the tag carries no notes of its
own.
The one rule: bump before you tag
The tag must point at the version-bump commit. Cutting the tag first and bumping afterward leaves the tag on a commit whose in-code version is still the previous release — this skill exists because that exact mistake happened once. Do the changelog and the version bump in the release commit, then tag that commit.
Version sources — all must read the same number
Three files hold the version. The release-build scripts
(scripts/release-binaries.ts, scripts/stage-npm-packages.ts) refuse to build
if they drift, so keep them in lockstep:
shared/version.ts—R3_VERSION(baked into the binary + CLI, reported by/api/health; the CLI warns on skew).package.json— top-level"version".npm/package.json—"version"and all fouroptionalDependenciespins:@hyperlogue/r3-darwin-arm64,-darwin-x64,-linux-x64,-linux-arm64. All four must equal the new version (the launcher resolves the matching per-platform binary at exactly its own version).
Steps
-
Pick the version (SemVer). Previous tag:
git describe --tags --abbrev=0. -
Draft the CHANGELOG entry (
CHANGELOG.md, [Keep a Changelog] format). Survey what shipped since the last tag —git log v<prev>..HEAD --oneline— then:- Insert a new
## [X.Y.Z] - YYYY-MM-DDsection directly under the intro block, above the previous version. Use the release date. - Group bullets under
### Added/### Changed/### Fixed/### Removed— only the groups that apply, in that order. - Write from the user's vantage point: what they can now do, or no longer
run into — not the internal mechanics, refactors, or scaffolding that got it
there. Frame each entry as what shipped, not what was turned off or reworked
mid-development; internal churn a user never observes doesn't belong in the
log at all. Match the existing voice: a bold lead-in (
**Feature.**) then a sentence or two on the change and why it matters; fold related commits into one bullet. - Add the compare link at the very bottom, with the others:
[X.Y.Z]: https://github.com/hyperlogue/r3/compare/v<prev>...vX.Y.Z
- Insert a new
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.
- 8d ago Changed · +2 lines 7a5aa2175e77
- 16d ago Changed · -2 lines f00563bd70b3
- 25d ago Changed · +6 lines 67c79e41fade
- 29d ago Changed · +11 lines eeee8ae15bde
- 1mo ago Changed 172113584132
- 1mo ago First seen · 141 lines · 81 tokens per session scan A 436e30480346
release is a skill published in the GitHub repository hyperlogue/r3 (45 stars, last pushed today), licensed MIT. It adds 81 tokens to every session and 2,093 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
ring:generating-release-guides
Generating an internal Operations-facing update/migration guide from the git diff between two refs, documenting per-change client impact, deploy ordering, monitoring, and rollback notes in English, pt-br, or both. Use when preparing a version release or recording what changed for the Ops team. Runs read-only by…
pr-triage
4-phase PR backlog management with audit, deep code review, validated comments, and optional worktree setup. Use when triaging pull requests, catching up on pending code reviews, or managing a backlog of open PRs. Args: 'all' to review all, PR numbers to focus (e.g. '42 57'), 'en'/'fr' for language, no arg = audit…
review-pr
Perform a comprehensive code review of a pull request.
pr
Analyze changes, detect scope issues, and create a well-structured PR.
validate-changes
Evaluate staged changes using LLM-as-a-Judge before committing.
address-github-comments
Use when you need to address review or issue comments on an open GitHub Pull Request using the gh CLI.