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/forcedotcom/sf-skills/dx-code-analyzer-runnpx skills add forcedotcom/sf-skills --skill dx-code-analyzer-rungit clone --depth 1 https://github.com/forcedotcom/sf-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/skills/forcedotcom/sf-skills/dx-code-analyzer-run)<a href="https://agentmods.dev/skills/forcedotcom/sf-skills/dx-code-analyzer-run"><img src="https://agentmods.dev/badge/skills/forcedotcom/sf-skills/dx-code-analyzer-run.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 | $0.00239 | $0.06690 |
| Opus 5 | $0.00120 | $0.03345 |
| Sonnet 5 | $0.00048 | $0.01338 |
| Haiku 4.5 | $0.00024 | $0.00669 |
Grade A, and why
dx-code-analyzer-run 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 yesterday.
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 — 538 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Running Code Analyzer Skill
CRITICAL: Mandatory Script Usage
Every interaction with Code Analyzer results MUST go through the bundled scripts in <skill_dir>/scripts/. No exceptions.
WRONG — never do this:
# WRONG: inline Python to parse results
python3 -c "import json; data = json.load(open('results.json'))..."
# WRONG: inline Node.js to parse results
node -e "const data = require('./results.json')..."
# WRONG: jq to filter results
cat results.json | jq '.violations[] | select(.engine=="pmd")'
# WRONG: reading the results file directly (it can be 10MB+)
Read tool → code-analyzer-results-*.json
Also forbidden: run_code_analyzer and any mcp__* tool — Bash only.
RIGHT — always do this:
# Summarize scan results
node "<skill_dir>/scripts/parse-results.js" "./code-analyzer-results-TIMESTAMP.json"
# Filter/rank/query results (by engine, severity, file, rule, category)
node "<skill_dir>/scripts/query-results.js" "./code-analyzer-results-TIMESTAMP.json" --engine pmd --summary
# List/browse available rules (by engine, category, language, severity)
node "<skill_dir>/scripts/list-rules.js" "Security" --top 10
# Look up what a rule means
node "<skill_dir>/scripts/describe-rule.js" "ApexCRUDViolation" --engine pmd
# Discover fixable violations
node "<skill_dir>/scripts/discover-fixes.js" "./code-analyzer-results-TIMESTAMP.json"
# Apply fixes (after user confirms)
node "<skill_dir>/scripts/apply-fixes.js" "./code-analyzer-results-TIMESTAMP.json"
# Summarize applied fixes
node "<skill_dir>/scripts/summarize-fixes.js" "./code-analyzer-results-TIMESTAMP.json"
# Filter vendor files (jQuery, Bootstrap, *.min.js) before applying fixes
node "<skill_dir>/scripts/filter-violations.js" "./code-analyzer-results-TIMESTAMP.json" "./code-analyzer-results-TIMESTAMP-filtered.json" --report
<skill_dir> is the absolute path to the directory containing this SKILL.md. Never use ./scripts/ — that resolves against the user's CWD, not the skill dir.
What ships with it
23 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- examples/basic-scan-output.json 2.3 KB
- examples/command-variations.md 9.6 KB
- examples/fix-application-before-after.md 3.4 KB
- examples/large-scan-output.json 2.2 KB
- examples/README.md 1.8 KB
- examples/security-focused-output.json 2.5 KB
- references/command-examples.md 3.3 KB
- references/engine-reference.md 1.3 KB
- references/error-handling.md 1.7 KB
- references/flag-reference.md 4.7 KB
- references/post-scan-workflows.md 7.9 KB
- references/quick-start.md 1.1 KB
- references/special-behaviors.md 4.6 KB
- references/vendor-file-handling.md 6.9 KB
- scripts/apply-fixes.js 4.4 KB runs code
- scripts/describe-rule.js 12 KB runs code
- scripts/discover-fixes.js 1.0 KB runs code
- scripts/filter-violations.js 12 KB runs code
- scripts/list-rules.js 7.9 KB runs code
- scripts/parse-results.js 2.1 KB runs code
- scripts/query-results.js 7.2 KB runs code
- scripts/summarize-fixes.js 1000 B runs code
- scripts/verify-execution.sh 863 B runs code
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.
- yesterday First seen · 538 lines · 239 tokens per session scan A 47b51d3d0a4f
dx-code-analyzer-run is a skill published in the GitHub repository forcedotcom/sf-skills (964 stars, last pushed today), licensed Apache-2.0. It adds 239 tokens to every session and 6,690 once invoked, about $0.0012 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 2026-09-03.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…