Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/me2resh/apexyardnpx agentmods add skills/me2resh/apexyard/releaseWrote 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/me2resh/apexyard/release)<a href="https://agentmods.dev/skills/me2resh/apexyard/release"><img src="https://agentmods.dev/badge/skills/me2resh/apexyard/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/me2resh/apexyard/release"><img src="https://agentmods.dev/badge/skills/me2resh/apexyard/release.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 5 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 Anti-Refusal · line 133 Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.Fix: Remove instructions that suppress warnings, disclaimers, or ethical commentary. Let the agent surface safety-relevant caveats to the user.
- high Prompt Injection · line 236 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
- medium Agent Snooping · line 162 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 416 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 417 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00033 | $0.08514 |
| Opus 5.5 | $0.00013 | $0.03406 |
| Sonnet 5.5 | $0.00007 | $0.01703 |
| Haiku 4.5 | $0.00003 | $0.00851 |
Grade A, and why
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 13d 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 — 468 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/release — Cut an apexyard release
Generated release PR descriptions and release notes are durable, human-facing
artefacts. Read .claude/rules/writing-standard.md. Use the controlled technical writing profile:
lead with the outcome and next action, use plain concise prose, and remove empty
sections.
Standardises the dev → main release flow introduced by AgDR-0007. Reads the conventional-commit log between main and dev, proposes a semver bump, generates and writes the CHANGELOG entry, opens the release PR (dev→main), and triggers the auto-tag-on-release-pr-merge GitHub Actions workflow that tags the squash commit and creates a GitHub Release after merge. One command drives the operator from "nothing" to "PR open, ready for Rex + CEO". The tag and GitHub Release entry are created automatically by CI when the PR merges. The release PR also records a Released-From trailer with the exact dev cut-point SHA, and the changelog step warns loudly if commits inside the resolved changelog range aren't all making it into entries — both guard against the #872 changelog-truncation failure mode. Design rationale: AgDR-0076, AgDR-0094.
This skill is framework-only — it's for cutting apexyard releases, not for releasing managed projects under governance. Managed projects stay trunk-based and don't have a release-cut flow.
Usage
/release # auto-detect bump from conventional commits
/release v1.2.0 # explicit version, skip auto-detect
/release --dry-run # preview changelog + PR body without writing any files
/release --dry-run v1.2.0
Process
1. Pre-flight
Verify:
- Current repo IS the apexyard framework (origin or upstream is
me2resh/apexyard). Refuse otherwise — this skill is framework-only. - Working tree is clean. Refuse if uncommitted changes.
devbranch exists (git rev-parse --verify upstream/dev). Refuse if absent — adopt the dev/main model first.devis ahead ofmainby ≥ 1 commit. Refuse if equal — nothing to release.
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.
- 13d ago Changed · +13 lines 64a09e6ba5d7
- 29d ago Changed · +26 lines f2c25685e63f
- 1mo ago Changed · +7 lines 08f7e4874d24
- 2mo ago First seen · 422 lines · 33 tokens per session scan A 7d0d61009ca2
release is a skill published in the GitHub repository me2resh/apexyard (542 stars, last pushed yesterday), licensed MIT. It adds 33 tokens to every session and 8,514 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 2026-09-03.
release compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| releaseme2resh/apexyard | Skill | 542 | yesterday | MIT | A | 33 | Claude Code |
| releaseparcadei/Continuous-Claude-v3 | Skill | 3.9k | 9mo ago | MIT | A | 20 | Claude Code |
| releaseYeachan-Heo/oh-my-claudecode | Skill | 41k | yesterday | MIT | A | 27 | Claude Code |
| changelog-generatordecebals/claude-code-java | Skill | 770 | 8d ago | MIT | A | 40 | Claude Code, Codex |
| releaseoliver-kriska/claude-elixir-phoenix | Skill | 574 | yesterday | MIT | A | 60 | Claude Code |
| ln-62-release-publisherlevnikolaevich/claude-code-skills | Skill | 587 | yesterday | MIT | A | 24 | Claude Code |
| land-and-deployFlorianBruniaux/claude-code-ultimate-guide | Skill | 6.4k | 2d ago | CC-BY-SA-4.0 | A | 24 | Claude Code |