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-whygit 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-why)<a href="https://agentmods.dev/skills/codecast-sh/codecast/cast-why"><img src="https://agentmods.dev/badge/skills/codecast-sh/codecast/cast-why/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-why"><img src="https://agentmods.dev/badge/skills/codecast-sh/codecast/cast-why.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 | $0.00071 | $0.00466 |
| Opus 5.5 | $0.00028 | $0.00186 |
| Sonnet 5.5 | $0.00014 | $0.00093 |
| Haiku 4.5 | $0.00007 | $0.00047 |
Grade A, and why
cast-why 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
git blame answers who. This answers why, with the conversation that produced the line.
Find the session
cast blame --porcelain <file>:<line> # one line
cast blame --porcelain -L <a>,<b> <file> # a block; group the lines by session
Each attributed line carries cast-session (short id), cast-message,
cast-url, cast-title and cast-author beside the git fields.
A line with git fields only predates attribution: use the commit summary and
cast search "<summary or key identifiers>" to find the session by hand, and
say plainly when there is none.
Read the reasoning
cast read '<cast-url>#msg-<cast-message>' -c 6
Widen the window (-c 20) when the decision was made earlier than the edit.
The message is where the file was written; the why is usually a few turns
before it, in the user's ask or in the assistant's plan. For a block written by
several sessions, read each and note the order: the later session may have
changed the intent of the earlier one.
Answer
Lead with the intent in the author's words, quoted, with the session short id
so it renders as a live reference. Then, only if the history shows them: the
alternatives considered, what depended on this choice, and whether a later
session changed it. Mint a link the reader can open with
cast link <session> <message line>.
Do not guess. If the transcript does not contain a reason, say the line is attributed but unexplained, and offer what the surrounding code suggests as a separate, clearly marked inference.
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 · 71 tokens per session scan A 1eed9db337c5
cast-why is a skill published in the GitHub repository codecast-sh/codecast (40 stars, last pushed today), licensed MIT. It adds 71 tokens to every session and 466 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
to-pr
Gate, push, and open a GitHub pull request on the repo's PR template, then watch CI.
deploy-check
MUST use before any git push to main/master/production, or when user mentions 'deploy', 'going live', 'push to prod', 'ready to ship', 'merge to main', 'release'. Also trigger before any npm publish for CLI tools, or on 'audit', 'check vulnerabilities', 'are our deps safe?', 'npm audit', 'yarn audit'. Performs: test…
changelog
Generate a changelog from git history since a tag, date, or commit.
pr-review
Review and post feedback on a GitHub or Gitea pull request end-to-end: fetch the PR diff, run a multi-agent code review, and auto-post the verdict as a real PR review (approve/request-changes/comment) via the platform's API. Triggers on: 'review this PR', 'review PR #N', 'check this pull request', 'post a PR review'…
github-project-management
Comprehensive GitHub project management with swarm-coordinated issue tracking, project board automation, and sprint planning.
agentic-jujutsu
Quantum-resistant, self-learning version control for AI agents with ReasoningBank intelligence and multi-agent coordination.