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 firelock-ai/kin --skill blast-radius-reviewgit clone --depth 1 https://github.com/firelock-ai/kinWrote 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/firelock-ai/kin/blast-radius-review)<a href="https://agentmods.dev/skills/firelock-ai/kin/blast-radius-review"><img src="https://agentmods.dev/badge/skills/firelock-ai/kin/blast-radius-review/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/firelock-ai/kin/blast-radius-review"><img src="https://agentmods.dev/badge/skills/firelock-ai/kin/blast-radius-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00060 | $0.00814 |
| Opus 5 | $0.00030 | $0.00407 |
| Sonnet 5 | $0.00012 | $0.00163 |
| Haiku 4.5 | $0.00006 | $0.00081 |
Grade A, and why
blast-radius-review 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 — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reviewing a change by its blast radius
A line diff says what text moved. It does not say what the change can reach. Kin's graph does, because it holds the call, import, and reference edges between entities, so the downstream set is walked rather than guessed.
Use this when you are reviewing someone else's change, sizing your own before you make it, or being asked whether an edit is safe.
The workflow
1. Name the entities the change touches. Work from the diff's file and symbol names.
Resolve each one with semantic_search to get its stable entity id, kind, and signature.
Overloads and same-named symbols in different files are different entities, so carry the
ids forward rather than the names.
2. Walk the downstream set. Call impact_analysis on each changed entity. It returns
the downstream entities the change can reach through the relation graph. That set, not the
diff, is the review surface. graph_neighborhood with direction set to in gives the
same shape when you want the immediate dependents at a chosen depth.
3. Confirm the call sites. find_references returns everything that imports, calls, or
references the entity. Use it to separate real callers from name collisions, and to catch
callers that impact_analysis reached at a depth you did not walk.
4. Follow the paths that carry data. For anything touching a value's shape, a parsing
step, or a security boundary, run trace_data_flow from the changed entity. It returns the
ordered chain of steps rather than a flat neighborhood, so you can see how far a changed
value actually travels and where it is consumed.
5. Read only what the radius earned. Pull get_context_pack on the affected entities
you must actually judge, and get_entity_source when you need one body. Do not read whole
files to reconstruct context the pack already carries.
6. Ask who owns the history. kin_provenance_query reports an entity's change count,
its latest change, and the approvals recorded against it. A hot entity with no recorded
approvals is worth flagging on its own.
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 · 65 lines · 60 tokens per session scan A be7a1cbe1530
blast-radius-review is a skill published in the GitHub repository firelock-ai/kin (47 stars, last pushed today), licensed Apache-2.0. It adds 60 tokens to every session and 814 once invoked, about $0.0003 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 skills, from other repositories
sem
Use sem to get entity-level (function/class/method) semantic diffs, impact analysis, blame, and dependency context from any Git repo. Trigger this skill whenever the user asks what changed in a commit or PR, wants to understand the blast radius of a change, needs to know who last modified a function, wants to trace…
sem
Semantic version control CLI. Entity-level diffs for Git (functions, classes, methods instead of lines).
writing-rust
Idiomatic Rust development. Use when writing Rust code, Cargo crates/workspaces, Rust tests, or rustfmt/clippy/cargo workflows. Emphasizes ownership, Result errors, small APIs, stdlib-first dependencies, fast cargo feedback, and behavior tests. NOT for Go, Python, TypeScript, shell scripts, or infra-only work.
architect-review
use when user ask to review spec.
data-integrity-review
Data integrity specialist for schema correctness, owner isolation, projections, hash chains, log separation, snapshots, and replay consistency. Use when validating that data remains correct under sync and persistence rules.
anvien-pr-review
Use when the user wants to review a pull request, understand what a PR changes, assess risk of merging, or check for missing test coverage. Examples: "Review this PR", "What does PR #42 change?", "Is this PR safe to merge?".