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 Parcha-ai/parcha-skills --skill verify-releasegit clone --depth 1 https://github.com/Parcha-ai/parcha-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/parcha-ai/parcha-skills/verify-release)<a href="https://agentmods.dev/skills/parcha-ai/parcha-skills/verify-release"><img src="https://agentmods.dev/badge/skills/parcha-ai/parcha-skills/verify-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/parcha-ai/parcha-skills/verify-release"><img src="https://agentmods.dev/badge/skills/parcha-ai/parcha-skills/verify-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 | $0.00076 | $0.01081 |
| Opus 5.5 | $0.00030 | $0.00432 |
| Sonnet 5.5 | $0.00015 | $0.00216 |
| Haiku 4.5 | $0.00008 | $0.00108 |
Grade A, and why
verify-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 1mo 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 — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Verify release
Establish that the intended change is serving in the intended environment and that its agreed behavior works there. Keep the verification proportional to the change. Use the repository's existing deployment tools, tests, and observability; no particular provider, framework, browser, or telemetry service is required.
Carry forward the request
Recover the target environment, candidate release, expected behavior, selected checks, and existing authorization from the request and any tracker or handoff. Inspect deployment configuration and the relevant diff only as needed to fill gaps. Ask only for a consequential choice you cannot establish; do not repeat settled scope or permission questions.
Identify the components and dependencies that actually serve the selected path. Do not make unrelated or intentionally disabled services gates. Keep environments and test identities separate. A preview result proves only what that preview exercised.
Establish the live candidate
Map the intended change to an immutable deployed identity: commit, image digest, build ID, package version, or equivalent. Use the release manifest when components have different versions; do not require every component to share one SHA. A merge commit may differ from the PR head: establish the mapping instead of assuming a mismatch or equivalence.
Check the deployment's state and its running artifact, not merely a green CI job or a completed deploy label. Where available, corroborate with a live version endpoint or fresh runtime evidence. A missing version endpoint is not itself a defect if another trustworthy source proves the running artifact. If identity cannot be established, report that gap instead of claiming the candidate passed.
If rollout is still progressing, use bounded waits appropriate to its normal duration and continue independent checks. Resume dependent checks as soon as their prerequisites pass. Stop unchanged retries when evidence shows failure, unavailable access, or an exhausted execution limit. State the next diagnostic or resumption condition. Claim ongoing monitoring only when a real monitor is running, with an owner and a way to retrieve its result; otherwise save a resumable checkpoint.
What ships with it
1 file 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.
- 1mo ago First seen · 45 lines · 76 tokens per session scan A 5fea2cf265ed
verify-release is a skill published in the GitHub repository Parcha-ai/parcha-skills (126 stars, last pushed 15d ago), licensed MIT. It adds 76 tokens to every session and 1,081 once invoked, about $0.0003 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 2026-09-17.
verify-release compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| verify-releaseParcha-ai/parcha-skills | Skill | 126 | 15d ago | MIT | A | 76 | Claude Code, Codex |
| imagegenopenai/codex | Skill | 134k | today | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | today | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | today | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 314k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 103 | Claude Code |