blast-radius
Analyzes code change impact with risk scoring and affected-node mapping. Use before merging to understand what a change touches and what lacks test coverage.
Install / Use
npx skills add athola/claude-night-market --skill blast-radiusInstalls into whichever agent you are using.
SKILL.md
Installable skill definition
Quality Score
Category
Development & EngineeringSupported Platforms
Our assessment of blast-radius
blast-radius scores 81/100 on our quality scale, 3569th of 4,716 Development & Engineering skills we index.
Its SKILL.md is 4.6 KB long, split into 7 sections with 1 code example: a solid amount of guidance for an agent.
It has 338 GitHub stars, a meaningful sign that others use it.
Maintenance, license and trust
- The repository was last updated about 2 months ago, so blast-radius is actively maintained.
- Our last check on 2026-11-08 found the source still online.
- It is released under the MIT license, a permissive license that allows use, modification and commercial use with attribution.
- Its trust signals score 100/100, with no cautions. These come from repository metadata, not a code audit — read the skill file before letting an agent act on it.
Safety scan
No issues foundOur scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful.
AI review by kimi-k2.7-code on 2026-10-26. Automated pattern scan on 2026-10-26. It catches known dangerous patterns, not every risk — read a skill before letting an agent act on it.
blast-radius compared with similar skills
All 4 of these similar skills score higher than blast-radius; compare them before choosing.
| Skill | Score | Stars | Updated | Format |
|---|---|---|---|---|
| blast-radius (this skill)by athola | 81 | 338 | 57d ago | SKILL.md |
| taste-skillby Leonxlnx | 100 | 118.9k | 11d ago | CLAUDE.md |
| hyperframesby heygen-com | 100 | 87.1k | today | CLAUDE.md |
| ai-job-searchby ai-job-search-dev | 100 | 72.6k | today | CLAUDE.md |
| claude-howtoby luongnv89 | 100 | 47.5k | 5d ago | CLAUDE.md |
Frequently asked questions
- How do I install blast-radius?
- Run
npx skills add athola/claude-night-market --skill blast-radius. The install tabs above show the steps for each supported agent. - Which AI agents does blast-radius work with?
- It is written for Universal, as a SKILL.md file. Other agents that read the same format can often use it too.
- Is blast-radius safe to use?
- Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful. It is MIT-licensed and scores 100/100 on trust signals. Skills are instructions an agent will follow, so read the file before installing it and do not approve commands you do not understand.
- Is blast-radius still maintained?
- The repository was last updated about 2 months ago, so blast-radius is actively maintained.
Skill content
View source on GitHubname: blast-radius role: entrypoint description: Analyzes code change impact with risk scoring and affected-node mapping. Use before merging to understand what a change touches and what lacks test coverage. model_hint: standard tags:
- code-review
- impact-analysis
- risk-scoring tools: [] dependencies:
- imbue:review-core
- imbue:structured-output
Blast Radius Analysis
Analyze the impact of current code changes using the code knowledge graph.
When NOT To Use
- Reading the changed code for defects (use
pensive:bug-review) - The code graph is missing or stale (use
gauntlet:graph-build)
Prerequisites
This skill requires the gauntlet plugin for graph data. Check if it's available:
GRAPH_QUERY=$(find ~/.claude/plugins -name "graph_query.py" -path "*/gauntlet/*" 2>/dev/null | head -1)
If gauntlet is not installed (GRAPH_QUERY is empty):
Fall back to a manual impact analysis using git diff
and grep to trace imports and call sites. Skip graph
steps and go directly to step 3 (manual mode).
If gauntlet is installed but no graph.db exists:
Tell the user: "Run /gauntlet-graph build first."
Steps
-
Show current changes: Run
git diff --statto show the user what files changed. -
Run impact analysis (requires gauntlet):
python3 "$GRAPH_QUERY" \ --action impact --base-ref HEAD --depth 2Fallback tier 1 (sem available, no gauntlet): Use sem for cross-file dependency tracing:
if command -v sem &>/dev/null; then sem impact --json <changed-file> fiThis traces real function-level dependencies instead of filename matching. See
leyline:sem-integrationfor detection patterns.Fallback tier 2 (no sem, no gauntlet): Trace callers of changed functions with rg (or grep):
# Prefer rg for speed; fall back to grep if command -v rg &>/dev/null; then git diff --name-only HEAD | while read f; do stem="${f%.*}"; stem="${stem##*/}" [ -z "$stem" ] && continue # skip dotfiles (.gitignore etc.) rg -l "$stem" . 2>/dev/null done | sort -u else git diff --name-only HEAD | while read f; do stem="${f%.*}"; stem="${stem##*/}" [ -z "$stem" ] && continue # skip dotfiles (.gitignore etc.) grep -rl "$stem" . 2>/dev/null done | sort -u fiNote: this searches all file types. For Python-only projects, add
--type pytorgor--include="*.py"togrepto reduce false positives. -
Display results in priority order:
Format the output as a table:
Risk | Node | File | Anchor | Reason 0.85 | auth.py::verify_token | auth.py:45 | `def verify_token(token):` | untested, security 0.62 | db.py::execute_query | db.py:112 | `cursor.execute(query, params)` | high fan-in 0.41 | api.py::handle_request | api.py:78 | `def handle_request(req):` | flow participantThe
Anchorcolumn is the verbatim source text at the cited line. It lets a reviewer confirm the finding without re-running the tool. -
Highlight untested functions: List any affected functions that lack test coverage (no TESTED_BY edge).
-
Show overall risk: Display the overall risk level (low/medium/high) based on the maximum risk score.
-
Suggest actions:
- For high-risk nodes: "Consider adding tests before merging"
- For security-sensitive nodes: "Review authentication and authorization logic carefully"
- For high-fan-in nodes: "Changes here affect many callers; verify backward compatibility"
Verify Findings Are Grounded (blast-radius:findings-verified)
Write findings to .review/findings.json, run the citation verifier
(Skill(imbue:review-core) Step 5), and drop or label UNVERIFIED any
the verifier rejects.
Exit Criteria
- [ ] Results table lists every affected node with a
File(file:line) and verbatimAnchorcolumn. - [ ] Overall risk level (low/medium/high) is displayed based on the maximum risk score.
- [ ] Every reported finding carries a
Location+ verbatimAnchorconfirmed bycitation_verifier.py(exit0), or unverified findings were dropped or labeledUNVERIFIED.
Risk Scoring Model
Five weighted factors (sum capped at 1.0):
| Factor | Weight | Meaning | |--------|--------|---------| | Test gap | 0.30 | No test coverage | | Security | 0.20 | Auth/crypto/SQL keywords | | Flow participation | 0.25 | Part of execution flows | | Cross-community | 0.15 | Called from other modules | | Caller count | 0.10 | High fan-in function |
Related Skills
taste-skill
118.9kAgent skills that give coding agents taste: art direction, reference images and a browser check instead of generic AI pages
hyperframes
87.1kAI video you can actually edit. HyperFrames is a free, open-source AI video editor. Describe any video and get a real project you can change down to the frame.
ai-job-search
72.6kThe job search that runs on your machine. AI job application framework built on Claude Code: evaluate postings, tailor CVs, write cover letters, prep interviews. Fork it and own it.
claude-howto
47.5kA visual, example-driven guide to Claude Code — from basic concepts to advanced agents, with copy-paste templates that bring immediate value.
Languages
Trust signals
From repository metadata: license, adoption, age and documentation. Not a code audit — see the Safety scan above for what the skill file itself contains.
