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 agentmods add skills/prabhdeepsingh/claude-plugins/blast-radiusnpx skills add PrabhdeepSingh/claude-plugins --skill blast-radiusgit clone --depth 1 https://github.com/PrabhdeepSingh/claude-pluginsWrote 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/prabhdeepsingh/claude-plugins/blast-radius)<a href="https://agentmods.dev/skills/prabhdeepsingh/claude-plugins/blast-radius"><img src="https://agentmods.dev/badge/skills/prabhdeepsingh/claude-plugins/blast-radius.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 | $0.00096 | $0.02655 |
| Opus 5 | $0.00048 | $0.01327 |
| Sonnet 5 | $0.00019 | $0.00531 |
| Haiku 4.5 | $0.00010 | $0.00265 |
Grade A, and why
blast-radius 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 4d 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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Blast Radius — who reads the thing you're changing?
A change can be locally correct, fully tested, and still break production — because the correctness of a producer says nothing about the assumptions of its consumers. And the most expensive version of that break isn't the loud one; it's the silent one, where a downstream catch or fallback converts the breakage into missing data that nobody notices for weeks, long after the deploy that caused it has stopped being a suspect. This skill exists to make "who reads this?" a mandatory step in the change, not an instinct you hope the author has.
When to apply this
Apply it the moment a change alters the shape, format, semantics, or published identity of anything consumed outside the edited code: a function's return value or type, an API or tool response body, a serialized payload, a database column other code reads, a log or telemetry field, an event or queue message, a config value or env var, CLI/stdout output that anything parses, or an identifier a caller addresses by name (a tool, route, or command). Wrapping counts. Renaming counts — a field or an identifier. Adding an envelope around existing data counts — the bytes a consumer parses are different even though "the data is still there."
Skip it for changes with genuinely no consumers outside the edited function, and for strictly additive optional fields that no consumer is required to read.
The test is not "did I change an interface file" — it's "does anything outside this diff read the bytes, fields, or values I'm changing, or address something by the name I'm changing?" If you haven't checked, the answer is unknown, and unknown means yes.
Run sections 1–6 in order. They're cheap — a few searches and one real observation — and each exists because skipping it has a specific failure mode.
1. Name the seam
Before editing, state in one sentence what contract is changing: the producer, and either the data shape and transport (return value / response body / column / log field / event / stdout) or the published identity (tool, route, command) a caller addresses by name. Why: an unnamed seam can't be searched for. "I'm changing how search results come back" is a vibe; "the tool's text channel currently carries raw JSON that callers parse" is a searchable surface with findable consumers.
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.
- 4d ago First seen · 81 lines · 96 tokens per session scan A 88627d5d1ef0
blast-radius is a skill published in the GitHub repository PrabhdeepSingh/claude-plugins (3 stars, last pushed 4d ago), licensed MIT. It adds 96 tokens to every session and 2,655 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
design-everyday-things
Apply foundational design principles: affordances, signifiers, constraints, feedback, and conceptual models. Use when the user mentions "why is this confusing", "affordance", "error prevention", "discoverability", "human-centered design", "mental model", "mapping", "seven stages of action", "users keep making…
create-app
Guided journey from a raw app idea to a validated, cleanly architected first version that ships on a sustainable cadence. Orchestrates ten skills phase by phase - lean-startup, design-sprint, clean-architecture, domain-driven-design, clean-code, pragmatic-programmer, system-design, ios-hig-design, 37signals-way…
create-business
Guided journey from raw idea to a validated, positioned, priced business with a chosen beachhead. Orchestrates ten skills phase by phase - jobs-to-be-done, mom-test, design-sprint, lean-startup, good-strategy-bad-strategy, blue-ocean-strategy, obviously-awesome, hundred-million-offers, monetizing-innovation…
clean-architecture
Structure software around the Dependency Rule: source code dependencies point inward from frameworks to use cases to entities. Use when the user mentions "architecture layers", "dependency rule", "ports and adapters (hexagonal)", "onion architecture", "screaming architecture", "where should business logic go"…
cold-start-problem
Start and scale networked products using Andrew Chen's "The Cold Start Problem" framework for network effects. Use when the user mentions "network effects", "chicken and egg", "cold start", "two-sided marketplace", "atomic network", "hard side", "liquidity", "critical mass", "invite-only launch", "how do I get my…
influence-psychology
Apply the seven principles of ethical persuasion (reciprocity, commitment, social proof, authority, liking, scarcity, unity) to product design, copy, and sales. Use when the user mentions "social proof", "persuasive copy", "why users dont convert", "ethical persuasion", "reciprocity", "scarcity tactics", "commitment…