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 codecast-sh/codecast --skill cast-second-opiniongit clone --depth 1 https://github.com/codecast-sh/codecastWrote 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/codecast-sh/codecast/cast-second-opinion)<a href="https://agentmods.dev/skills/codecast-sh/codecast/cast-second-opinion"><img src="https://agentmods.dev/badge/skills/codecast-sh/codecast/cast-second-opinion/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/codecast-sh/codecast/cast-second-opinion"><img src="https://agentmods.dev/badge/skills/codecast-sh/codecast/cast-second-opinion.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 | $0.00052 | $0.00477 |
| Opus 5.5 | $0.00021 | $0.00191 |
| Sonnet 5.5 | $0.00010 | $0.00095 |
| Haiku 4.5 | $0.00005 | $0.00048 |
Grade A, and why
cast-second-opinion 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.
What it actually says
A reviewer that read the author's reasoning is biased by it. This hands a fresh model only the intent, the plan and the diff, then treats its findings as claims to verify, not verdicts.
Choose the reviewer
The argument names the agent. Otherwise prefer a different vendor from the
one running this session (cast exec --dry-run --agent codex shows whether
it is installed); fall back to the same vendor on a different model. Never the
same model that wrote the change.
Build the packet
- One paragraph of intent: what the change is for and what it must not break.
- The plan or task:
cast task context --currentorcast plan context --current. - The diff:
git diff-main(orgit diffplus staged changes when the alias is absent). Trim generated files and lockfiles. - The focus, if the user gave one.
Nothing else. No transcript, no reasoning, no list of what you already checked.
Run it
cast exec --agent <agent> --permission-mode default --timeout 10m - <<'PACKET'
You are reviewing a change you did not write. Read the intent, the plan and
the diff, then report, ranked by severity, with file and line for each:
correctness bugs, requirements in the plan the diff misses, simpler ways to
get the same result, and what you would test before merging. Be concrete.
Skip praise and restatement.
<intent, plan, diff, focus>
PACKET
Verify, then fold in
Check every finding against the code before accepting it. Fix the confirmed
ones or list them with a reason for deferring. Name the ones you rejected and
why, so the reader can see the review was weighed rather than obeyed. Record
the outcome on the task with cast task comment <id> when one is bound.
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 · 48 lines · 52 tokens per session scan A 6712e7623305
cast-second-opinion is a skill published in the GitHub repository codecast-sh/codecast (40 stars, last pushed today), licensed MIT. It adds 52 tokens to every session and 477 once invoked, about $0.0002 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 2026-09-15.
Other skills, from other repositories
adk-go-self-review
Review an ADK Go change the way a maintainer will — a fresh-context pass over the whole diff, five lenses (correctness and tests, scope, simplicity, style, adk-python parity), and the mutation check that proves your tests pin the change. Use before opening a PR, before any later push that changes code, and when asked…
honey-debt
Harvest honey shortcut markers into a debt ledger.
honey-review
Review a diff for over-engineering; terse delete-list.
review-full
Run a comprehensive multi-perspective code review on recent changes. Also triggers on 'is this secure?', 'security review', 'check for vulnerabilities', 'could this be exploited?' for security-focused review. Produces: GO/NO-GO verdict + findings table (Severity | Category | File:Line | Issue | Recommendation)…
review-diff
Scan git diffs for project-specific anti-patterns. Triggers on: 'scan diff', 'check diff', 'anti-pattern check', 'pattern scan', 'review changes'.
review
Fan out parallel read-only reviewers over a diff and consolidate one severity-ranked verdict.