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-rethinkgit 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-rethink)<a href="https://agentmods.dev/skills/codecast-sh/codecast/cast-rethink"><img src="https://agentmods.dev/badge/skills/codecast-sh/codecast/cast-rethink/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-rethink"><img src="https://agentmods.dev/badge/skills/codecast-sh/codecast/cast-rethink.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 | $0.00000 | $0.00490 |
| Opus 5.5 | $0.00000 | $0.00196 |
| Sonnet 5.5 | $0.00000 | $0.00098 |
| Haiku 4.5 | $0.00000 | $0.00049 |
Grade A, and why
cast-rethink 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
Execution drifts from intent one reasonable step at a time. This finds the intent again, from the record rather than from memory.
Name the work
git log --oneline -20, git diff-main --stat, and the bound task or plan
(cast task context --current, cast plan context --current). State in
one sentence what this feature is for. If that sentence is hard to write,
that is the first finding.
Excavate, in parallel
Fan out subagents, one per angle, each reporting a short brief:
- Origin:
cast context "<feature>"andcast search "<keywords>" -s 90dfor the session where it was first asked for. What problem was the human solving, in their words? - Decisions:
cast decisions --search "<keywords>"andcast search "decided|chose|went with|instead of"for every choice made along the way and its reason. - Attempts: every session that touched the files (
cast context --file <path>), what each tried, what it abandoned and why. - Board: the tasks and plans filed for it, what closed, what stalled.
- Current state: what the code does today versus the acceptance criteria.
Judge
Lay the origin next to the current direction. Then, in order: what the
intent is, where execution diverged from it and at which session, which
decisions still hold and which were made for reasons that no longer apply,
and what the right next step is: continue, adjust, or restart from a named
point. Record the conclusion on the plan or task (cast plan comment -d -r
or cast task comment) so the next session does not excavate again.
Do not write code in this skill. The output is the judgment.
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 · 42 lines · 0 tokens per session scan A 4a911ffb2d68
cast-rethink is a skill published in the GitHub repository codecast-sh/codecast (40 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 490 tokens. 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
google-agents-cli-scaffold
This skill should be used when the user wants to "create an agent project", "start a new ADK project", "build me a new agent", "add CI/CD to my project", "add deployment", "enhance my project", or "upgrade my project". Part of the agents-cli skills suite. Covers agents-cli scaffold create, scaffold enhance, and…
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…
grocery-prices
A skill to calculate grocery prices with country-specific taxes.
honey-px
Read huge read-only text as PNG pages; big input cut.
honey-memory
Per-project persistent memory files indexed in MEMORY.md.
debate
Weigh one risky change against a named alternative through an advocate, a skeptic, and a neutral investigator, then recommend.