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.
npx skills add BlacklineCloud/agent-skills --skill agent-skill-release-reviewgit clone --depth 1 https://github.com/BlacklineCloud/agent-skillsWrote 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/blacklinecloud/agent-skills/agent-skill-release-review)<a href="https://agentmods.dev/skills/blacklinecloud/agent-skills/agent-skill-release-review"><img src="https://agentmods.dev/badge/skills/blacklinecloud/agent-skills/agent-skill-release-review/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/blacklinecloud/agent-skills/agent-skill-release-review"><img src="https://agentmods.dev/badge/skills/blacklinecloud/agent-skills/agent-skill-release-review.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 | $0.00053 | $0.00546 |
| Opus 5 | $0.00026 | $0.00273 |
| Sonnet 5 | $0.00011 | $0.00109 |
| Haiku 4.5 | $0.00005 | $0.00055 |
Grade A, and why
agent-skill-release-review 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 9d 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 — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Skill Release Review
Overview
Use this skill to review a skill or plugin before it is published publicly. It is intended for maintainers who want a release-quality audit rather than a casual style pass.
Review Workflow
- Confirm the artifact type and release target.
- Identify whether the target is a skill, plugin, or mixed repo.
- Confirm whether the release target is Codex-only or multi-agent.
- Inspect trigger quality and scope.
- Check that
nameanddescriptionare specific, non-overlapping, and aligned with intended user requests. - Flag broad language that could cause false triggering or agent confusion.
- Check that
- Inspect source structure.
- Verify required files exist and optional resources are justified.
- Flag dead scaffolding, redundant docs, and generated files that should not be committed.
- Inspect release readiness.
- Check licensing, contribution docs, security policy, changelog, tests, and CI.
- Confirm that the public README explains what is shipped today, not just what might exist later.
- Report findings.
- Prioritize blocking issues first, then follow-up improvements.
- Distinguish required release blockers from non-blocking polish.
What to Focus On
Trigger Quality
- Is the skill description narrow enough to trigger only in the right situations?
- Is the skill name readable, stable, and consistent with folder naming?
- Would multiple skills in the same repo conflict or overlap?
Structure and Maintainability
- Does the artifact follow the expected folder layout?
- Are
references/,scripts/, andassets/used only when necessary? - Are generated or local-only files excluded from source control?
Public OSS Readiness
- Is the repository safe and comprehensible for outside contributors?
- Are release expectations, support boundaries, and security reporting clear?
- Does CI cover the actual contract that the project exposes?
Output Expectations
- Findings first, ordered by severity.
- Include file references when possible.
- Separate:
- release blockers
- correctness or maintainability issues
- optional polish
- If the artifact is ready, say so explicitly and note any residual risk.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 9d ago First seen · 68 lines · 53 tokens per session scan A 9110ea6da8d4
agent-skill-release-review is a skill published in the GitHub repository BlacklineCloud/agent-skills (1 stars, last pushed 3d ago), licensed MIT. It adds 53 tokens to every session and 546 once invoked, about $0.0003 per session on Opus 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 skills, from other repositories
review-code
Review code changes for correctness defects, regressions, security risks, data-integrity problems, concurrency hazards, and missing meaningful tests. Use for pull requests, branches, commits, patches, or working-tree reviews; do not use for implementation unless the user separately requests fixes.
review-security
Review application and infrastructure changes for exploitable security risks by tracing assets, trust boundaries, attacker-controlled input, authorization, sensitive data, and dangerous sinks. Use for security reviews, threat-focused PR reviews, authentication or authorization changes, input handling, secrets…
evidence-review
Review a small code or documentation change and return only evidence-backed correctness findings. Use in the Codex How To local plugin lab; do not modify files or post remote comments.
code-review-excellence
This skill should be used when the user asks to review a diff or pull request, write review comments, audit code quality, establish review standards, or improve how a team performs code review.
reviewee-judgment
Evaluates received review results before they generate work by separating problems from proposed fixes and comparing responses in a fixed decision order. Use whenever review results may lead to artifact changes; does not produce reviews.
recipe-review
Reviews completed implementation for governing-source compliance, scope economy, repository quality, and security, and applies user-approved corrections.