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 forcedotcom/sf-skills --skill experience-lwc-security-validategit 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/experience-lwc-security-validate)<a href="https://agentmods.dev/skills/forcedotcom/sf-skills/experience-lwc-security-validate"><img src="https://agentmods.dev/badge/skills/forcedotcom/sf-skills/experience-lwc-security-validate/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/forcedotcom/sf-skills/experience-lwc-security-validate"><img src="https://agentmods.dev/badge/skills/forcedotcom/sf-skills/experience-lwc-security-validate.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk pass
- NVIDIA SkillSpector pass
SkillSpector: 1 finding, up to low
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- low Privilege Escalation · line 96 Skill requests more permissions than appear necessary for its stated functionality. Review if elevated access is justified.Fix: Request only the minimum permissions required. Document why each permission is needed. Remove broad permissions like '*' or 'all'.
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 | $0.00249 | $0.02574 |
| Opus 5 | $0.00125 | $0.01287 |
| Sonnet 5 | $0.00050 | $0.00515 |
| Haiku 4.5 | $0.00025 | $0.00257 |
Grade A, and why
experience-lwc-security-validate 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 9d 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 — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Reviewing LWS Security
Run a structured Lightning Web Security (LWS) and Product Security compliance pass over a Lightning Web Component. Two output modes:
- Review mode (default) — severity-ranked findings + applied code fixes.
- Score mode — SARIF 2.1.0 JSON report keyed by the LWS rule catalog (
lws-001…lws-023b) for downstream gating, eval scoring, or CI ingest.
Both modes use the same detection rules from the references; only the output format differs.
When to Use
- The user asks for a "security review", "LWS check", "pre-ship security audit", or "compliance pass" on a specific LWC → review mode.
- The user asks to "score" a component's security or wants machine-readable findings to feed a gate or eval → score mode.
- Preparing a component for release and needing a unified security report.
- After implementing a fix, to verify no regression in security posture.
Do NOT use this skill for:
- Building new components (use
experience-lwc-generate). - Accessibility (apply WCAG 2.2 separately) or RTL review — out of scope.
- Gating a fix behind a feature flag (apply feature-flag gating after fixes land).
- Non-LWC security review (Apex, Aura, server-side) — out of scope.
Prerequisites
- Component path (LWC bundle under
modules/…). - Access to the component's JS/TS, HTML templates, CSS, and
.js-meta.xml. - Output mode:
review(default — find, fix, report) orscore(find, emit SARIF JSON, do NOT modify code). Confirm with the user before starting if it isn't obvious from the request.
Knowledge Bases
Each reference is the source of truth. Do not summarize from memory — open the reference, apply the guidelines, and cite the specific section you used in the report.
- Lightning Web Security (LWS) catalog: LWS Security Expert — blocked APIs and allowed alternatives.
- Rule catalog (
lws-001…lws-023b): Product Security Framework — for every rule the catalog gives the detection patterns and the canonical SARIFruleId/level/messagetemplate. Score mode emits one SARIF result per match using these exact values.
What ships with it
6 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.
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.
- 9d ago First seen · 153 lines · 249 tokens per session scan A 9acb419f1a06
experience-lwc-security-validate is a skill published in the GitHub repository forcedotcom/sf-skills (974 stars, last pushed yesterday), licensed Apache-2.0. It adds 249 tokens to every session and 2,574 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 2026-08-30.
Other skills, from other repositories
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…