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-learngit 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-learn)<a href="https://agentmods.dev/skills/codecast-sh/codecast/cast-learn"><img src="https://agentmods.dev/badge/skills/codecast-sh/codecast/cast-learn/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-learn"><img src="https://agentmods.dev/badge/skills/codecast-sh/codecast/cast-learn.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 | $0.00081 | $0.00513 |
| Opus 5.5 | $0.00032 | $0.00205 |
| Sonnet 5.5 | $0.00016 | $0.00103 |
| Haiku 4.5 | $0.00008 | $0.00051 |
Grade A, and why
cast-learn 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 correction that lives only in this transcript is made again by the next session. This moves it to where the next session looks first.
Harvest
Read back through this session for three kinds of learning:
- Corrections: moments the human said no, stop, not like that, or redirected the approach. Each is a rule the next session should already know.
- Decisions: a choice between approaches with a reason, whether the human made it or you did and they accepted it.
- Gotchas: a fact about this codebase or environment that cost time to find and is not written anywhere: a flag that must be set, a test that needs a service, a file that two systems own.
Skip anything derivable from the code or the git history, and anything that was true only for this task.
Route each one
- A rule that applies to every session in this repository goes into the project's agent instructions (CLAUDE.md or AGENTS.md) under the section that fits, in one or two sentences. Read the file first; edit an existing rule when one is close, never add a duplicate.
- A decision:
cast decisions add "<title>" --reason "<why>" --tags <area>. - A gotcha that needs more than two sentences:
cast doc create "<title>" -t insight -c -with the body on stdin, and one line in the instructions pointing at it. - A rule about how the human wants to be worked with, not about the code, goes into memory rather than the shared instructions.
With scan, list the candidates and the route for each without writing.
With write or no argument, write them and report what went where.
Keep the file short
Instruction files lose adherence as they grow. When an addition would push the file past a couple of hundred lines, tighten what is there before adding to it, and prefer a pointer to a doc over a paragraph.
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 · 46 lines · 81 tokens per session scan A abad9d0bbef6
cast-learn is a skill published in the GitHub repository codecast-sh/codecast (40 stars, last pushed today), licensed MIT. It adds 81 tokens to every session and 513 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 2026-09-15.
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.