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 markoblogo/abvx-agent-skills --skill public-release-verificationgit clone --depth 1 https://github.com/markoblogo/abvx-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/markoblogo/abvx-agent-skills/public-release-verification)<a href="https://agentmods.dev/skills/markoblogo/abvx-agent-skills/public-release-verification"><img src="https://agentmods.dev/badge/skills/markoblogo/abvx-agent-skills/public-release-verification/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/markoblogo/abvx-agent-skills/public-release-verification"><img src="https://agentmods.dev/badge/skills/markoblogo/abvx-agent-skills/public-release-verification.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00072 | $0.00881 |
| Opus 5 | $0.00036 | $0.00441 |
| Sonnet 5 | $0.00014 | $0.00176 |
| Haiku 4.5 | $0.00007 | $0.00088 |
Grade A, and why
public-release-verification 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 4d 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 — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Public Release Verification
Use this skill to decide what a release has actually proved. A green build is one input, not a public-release claim.
Verification Contract
Capture one evidence row for each applicable domain:
- repository/commit identity — repository, branch/tag, commit, and clean or intentionally dirty baseline;
- baseline and diff — starting state, changed scope, and unrelated-change check;
- build/package proof — tests, build, package contents, and metadata;
- deployment proof — deployment provider, deployment identifier, and completed status;
- HTTP/route proof — actual public URL, status code, redirects, and key routes;
- SEO/metadata proof — title, description, canonical, robots, and social metadata where applicable;
- browser desktop/mobile proof — real browser observations, responsive states, interaction, console, and network failures;
- locale/content proof — requested locales, visible strings, fallback behavior, and content constraints;
- device/runtime proof — real-device or runtime-specific observations where the release target is hardware or a constrained runtime;
- visual/public availability proof — screenshots or equivalent observed public rendering and availability window;
- human approval and cutover status — named approval evidence, approval scope, and whether DNS, traffic, or publication gates remain open.
Mark each row PROVEN, PARTIAL, BLOCKED, or UNKNOWN, with command,
URL, artifact path, timestamp, and verifier where available. Use N/A only
when the row genuinely does not apply and explain why.
Claim Rules
- Build proof is not live proof.
- Deployment proof is not HTTP proof.
- HTTP proof is not browser or visual proof.
- Browser proof is not owner approval or public cutover authorization.
- Missing evidence is
UNKNOWN, not success. - A final
PROVENclaim requires every applicable release-critical row to bePROVENand the human gate to be explicit. - Report
PARTIALwhen useful evidence exists but a release-critical row is incomplete; reportBLOCKEDwhen a required check failed or access prevents verification.
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.
- 4d ago Changed 0855c5081bc9
- 9d ago First seen · 95 lines · 72 tokens per session scan A 951e3e434489
public-release-verification is a skill published in the GitHub repository markoblogo/abvx-agent-skills (16 stars, last pushed yesterday), licensed MIT. It adds 72 tokens to every session and 881 once invoked, about $0.0004 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 2026-09-03.
Other skills, from other repositories
cli-e2e
Write, modify, or debug Docker-based Composio CLI end-to-end tests under ts/e2e-tests/cli, including binary invocation, fixture isolation, output assertions, and package manifests. Use for CLI E2E test suites only; use cli-command for CLI source implementation.
trace
Dispatch trace subagent to investigate unknown issues — reproduces, traces, and reports root cause for fix handoff.
codex-agent
Use when you want a second-opinion review via Codex CLI, cross-verification after another agent implements changes, debugging help, or alternative implementation proposals. Requires Codex CLI to be installed and authenticated.
css-debug
Use this skill to diagnose CSS and frontend layout issues such as positioning, overflow clipping, Tailwind class conflicts, z-index stacking, and React rendering visibility problems.
openlore-analyze-codebase
Run a full static OpenLore analysis and summarize architecture, call graph, refactoring issues, and duplicate code. Use when asked to analyze, map, or assess a codebase without LLM inference.
config-validator
Validate AIWG configuration files and project setup for correctness and completeness.