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-plangit 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-plan)<a href="https://agentmods.dev/skills/codecast-sh/codecast/cast-plan"><img src="https://agentmods.dev/badge/skills/codecast-sh/codecast/cast-plan/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-plan"><img src="https://agentmods.dev/badge/skills/codecast-sh/codecast/cast-plan.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 | $0.00078 | $0.00919 |
| Opus 5.5 | $0.00031 | $0.00368 |
| Sonnet 5.5 | $0.00016 | $0.00184 |
| Haiku 4.5 | $0.00008 | $0.00092 |
Grade A, and why
cast-plan 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 2d 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 — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Humans review plans hard and code lightly, because one wrong line of a plan becomes hundreds of wrong lines of code. This skill produces the artifact they review.
Find what already exists
Run these in parallel before asking anyone anything:
cast context "<the request>" # sessions that tried this or touched the area
cast search "<key terms>" -s 60d # earlier discussion, abandoned approaches
cast decisions --search "<key terms>" # decisions that constrain the design
cast plan ls -q "<topic>"; cast task ls -q "<topic>" # work already filed
Read the sessions that matter with cast read. Then explore the code the
change touches. Name, in one paragraph, what the earlier attempts learned and
what constraint each recorded decision imposes. A plan that repeats a
rejected approach without saying why is the failure this step exists to
prevent.
Interview
Ask only the questions the code and the history could not answer: the goal behind the request, what must not break, where the user wants to trade speed for completeness, and what done looks like. Ask them together, not one at a time. A question with an obvious answer wastes the human's attention; a guess on a question with a real fork wastes the whole plan.
Write the plan
cast plan create "<title>" -g "<goal in one sentence>" -a "<criterion>" -a "<criterion>" --body-file - <<'PLAN'
Context: what exists, what earlier attempts learned, which decisions bind.
Approach: the design, and the alternatives rejected with reasons.
Risks: what could go wrong and how each is checked.
PLAN
cast plan bind <plan_id>
Decompose into tasks that one session can finish alone, and write their order
as waves: one step per line, a blank line between waves. Steps in a wave run
in parallel; each wave needs every step of the one before. After ::, a
line carries the step's description: its acceptance criteria and the files
it owns.
cast plan steps <plan_id> - <<'STEPS'
Design the schema :: <acceptance criteria and owned files>
Build the API :: <...>
Build the UI :: <...>
Review in the real app :: <...>
STEPS
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.
- 2d ago Changed · +22 lines 9b6dbbc508bb
- 1mo ago First seen · 64 lines · 78 tokens per session scan A a830b8850214
cast-plan is a skill published in the GitHub repository codecast-sh/codecast (40 stars, last pushed today), licensed MIT. It adds 78 tokens to every session and 919 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-tickets
Slice a spec or a ticket into tracer-bullet tickets with blocking edges, saved to .specs/tickets/ .md.
to-spec
Turn the settled conversation into a spec (PRD) at .specs/specs/ .md.
register-project
Register an existing project in memory. Use when starting work on a new repo or when a project needs its own context file. Triggers on: 'register project', 'add project to memory', 'track this project', 'create project file'.
idea-vault
Cross-project idea capture and review. A notebook-with-reminders that logs the user's ideas, plans, and checklists across every project, in one plain-markdown file. Use this skill whenever the conversation contains a new idea, plan, or intention the user might want to save for later, and whenever a project milestone…
status
Show project status dashboard across registered repositories.
github-project-management
Comprehensive GitHub project management with swarm-coordinated issue tracking, project board automation, and sprint planning.