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 jhlee0409/omni-harness-kit --skill blast-radiusgit clone --depth 1 https://github.com/jhlee0409/omni-harness-kitWrote 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/jhlee0409/omni-harness-kit/blast-radius)<a href="https://agentmods.dev/skills/jhlee0409/omni-harness-kit/blast-radius"><img src="https://agentmods.dev/badge/skills/jhlee0409/omni-harness-kit/blast-radius/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/jhlee0409/omni-harness-kit/blast-radius"><img src="https://agentmods.dev/badge/skills/jhlee0409/omni-harness-kit/blast-radius.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 | $0.00121 | $0.01260 |
| Opus 5 | $0.00060 | $0.00630 |
| Sonnet 5 | $0.00024 | $0.00252 |
| Haiku 4.5 | $0.00012 | $0.00126 |
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 10d 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 — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
blast-radius — enumerate impact, surface the unknowns
You produce the impact set of a target symbol so a change can be made without missing a callsite. The honest contract of this skill: no tool guarantees omission-free discovery. LSP misses dynamic dispatch; grep misses renames; generated code and reflection defeat both. So you do NOT claim "completeness" — you guarantee all discovered edges, deduped with provenance, plus an explicit list of what you could not resolve. The unknowns section is the point, not an afterthought — it tells the human exactly where to look by hand.
1. Scope the target
Resolve the target symbol(s): a function / method / class / type / constant / API
route / DB field / component / exported name. For a signature or rename change,
capture BOTH the old and the new name. Note the declaring file:line.
2. Enumerate — layered, strongest signal first
Run every layer available; do not stop at the first. Cross-check the counts between layers — a divergence is itself a finding (a match one layer sees and another misses is a candidate omission).
- Code-intelligence (LSP / SCIP), if available — the strongest signal,
because it resolves bindings, not text:
references— every use of the symbol.implementations/ type hierarchy — every impl / subtype (for an interface or base type).- call hierarchy — incoming callers and outgoing callees; traverse recursively with a depth cap and a cycle guard. Record the provider and that support was present. If no LSP/index is available, say so explicitly (it changes the confidence of the result).
- AST inventory (tree-sitter), if available — enumerate declarations, imports/exports, class inheritance, and call-shaped expressions. Use it to catch structural uses and to sanity-check the LSP count.
- Text sweep (ripgrep) — always — grep both the old and new names across the
repo, excluding
node_modules,.venv,dist,build,.next,coverage, and vendored dirs. This catches string/symbol refs the import graph misses (config keys, DI tokens, dynamic route strings, docs). Treat lexical matches as candidates, never as resolved references — never present a grep hit as a precise call edge.
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.
- 10d ago First seen · 99 lines · 121 tokens per session scan A f899a640c227
blast-radius is a skill published in the GitHub repository jhlee0409/omni-harness-kit (2 stars, last pushed 1mo ago), licensed MIT. It adds 121 tokens to every session and 1,260 once invoked, about $0.0006 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
bug-finder
Hunt for one real, previously unreported defect and file it as a well-evidenced ticket — proactive discovery, not reactive diagnosis. INVOKE when asked to sweep code for bugs or hunt risky areas, and when /sonu:factory runs a bug-hunt pass. A known symptom is [[debugging]]; a pending diff is [[self-review]]. It files…
dekko-verify
Sanity-check a suspiciously low or zero call-graph result from dekko (getcallers, getcallees, findusages, impactedtests, unused) before concluding "no callers" or "dead code," or a heritage/throws-provenance result (query supertypes, query subtypes, query throws) that labels something (external) when you expect it to…
triage-report
Drain the .review/ report queue. Resolves un-triaged scan/audit reports (producer-agnostic — check-docs-consistency and any other scanner), dispatches the triage-report subagent (Sonnet) one report at a time for per-finding dispositions (promote / patch / dup / needs-investigation / dismiss), then the gateway absorbs…
silent-failure-hunter
Audits error-handling code in a pull request for silent failures, broad catch blocks, unjustified fallbacks, and unactionable error messages. Surfaces hidden failures users would otherwise hit in production. Use when reviewing PRs that add or modify try/catch, error callbacks, or fallback logic.
bug-sweep
Codebase bug hunt — find and fix AI-fixable bugs, defer the rest.
dogfood
Fix-through loop — invoke a new thing, fix bugs until it works.