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.
git clone --depth 1 https://github.com/alberduris/skillsWrote 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/commands/alberduris/skills/generate-plan)<a href="https://agentmods.dev/commands/alberduris/skills/generate-plan"><img src="https://agentmods.dev/badge/commands/alberduris/skills/generate-plan.svg" alt="Measured on agentmods" 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 | $0.00020 | $0.00482 |
| Opus 5 | $0.00010 | $0.00241 |
| Sonnet 5 | $0.00004 | $0.00096 |
| Haiku 4.5 | $0.00002 | $0.00048 |
Grade A, and why
generate-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 7d 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
Load the newspaper-explainer skill. Read ./templates/broadsheet.html and ./references/css-patterns.md to absorb the canonical structure, CSS class vocabulary, and palette. Then generate a broadsheet newspaper edition presenting a comprehensive implementation plan for: $@
Data gathering — understand the context before designing: a) parse the feature request extracting core problem, desired behavior, constraints, and scope boundaries, b) read the relevant codebase identifying files that need modification, existing patterns, related functionality, types and APIs to conform to, c) understand extension points (hooks, event systems, plugin architectures, configs, public APIs), d) check for prior art (similar features already implemented, existing code to reuse or extend).
Design phase — work through the implementation before writing HTML: a) state design (new state variables, existing state affected, state machine if behavior has multiple modes), b) API design (commands, functions, endpoints, signatures, error cases), c) integration design (interaction with existing functionality, hooks, events), d) edge cases (concurrent operations, error conditions, boundary values).
Verification checkpoint — before generating HTML, produce a structured fact sheet covering every state variable with type and purpose, every function/API with signature, every file needing modification with specific changes, every edge case with expected behavior, every assumption the plan relies on. Verify each against the code. Mark unverifiable items as uncertain. This fact sheet is your source of truth during HTML generation.
The LEAD STORY presents the feature's core problem and the proposed solution as investigative reporting. The floating INSET BOX carries scope metrics (files to modify, new functions, estimated complexity). SECONDARY STORIES cover individual design areas as separate articles: state design, API surface, integration points. The SIDEBAR presents the current-vs-proposed comparison as a structured widget and lists file references. LETTERS AND CORRESPONDENCE presents edge cases as questions and their resolutions. The DISPATCH BOARD surfaces implementation warnings (backward compatibility, performance considerations), test requirements grouped by category, and critical assumptions that need validation.
NEVER EVER fabricate facts — every claim must be traceable to actual code or the feature request. Write to ~/.agent/newspapers/ and open in the browser.
Ultrathink.
$@
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.
- 7d ago First seen · 19 lines · 20 tokens per session scan A 14861ce45326
generate-plan is a command published in the GitHub repository alberduris/skills (18 stars, last pushed 5mo ago), licensed MIT. It adds 20 tokens to every session and 482 once invoked, about $0.0001 per session on Opus 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 2026-08-30.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.