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 JasonBoy/msw-mcp --skill msw-cligit clone --depth 1 https://github.com/JasonBoy/msw-mcpWrote 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/jasonboy/msw-mcp/msw-cli)<a href="https://agentmods.dev/skills/jasonboy/msw-mcp/msw-cli"><img src="https://agentmods.dev/badge/skills/jasonboy/msw-mcp/msw-cli/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/jasonboy/msw-mcp/msw-cli"><img src="https://agentmods.dev/badge/skills/jasonboy/msw-mcp/msw-cli.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to medium
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 →
- medium Prompt Injection · line 70 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 77 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
- medium Prompt Injection · line 78 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
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 | $0.00041 | $0.01521 |
| Opus 5.5 | $0.00016 | $0.00608 |
| Sonnet 5.5 | $0.00008 | $0.00304 |
| Haiku 4.5 | $0.00004 | $0.00152 |
Grade A, and why
msw-cli scanned grade A with 1 finding 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 1mo 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
msw-cli add "http.get('*/api/user', async ({ request }) => { const res = await fetch(bypass(request)); const data = await res.json(); return HttpResponse.json({ ...data, role: 'admin' }) })" How it starts
The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
msw-cli
Dynamically add, update, and remove MSW handlers while the app keeps running. Run commands from the project directory (or pass -s <name> for a named session).
Project not set up yet? Use the msw-setup skill or run msw-cli setup first.
Agent guidelines
When using this skill to change mocks:
-
Do not edit local handler files (e.g.
handlers.ts,mocks/handlers).msw-cliappliesadd/update/remove/resetto the browser runtime over the WebSocket session. Changing on-disk handler modules is the wrong tool and can confuse the next dev reload. -
Before
open, check whether a session is already running: runmsw-cli list(all open sessions) and, if a session for this project already exists,msw-cli status(orstatus -s <name>) to see connection and handlers. Only runopenwhen no suitable session is active—avoid duplicate daemons for the same work.
Quick start
msw-cli open # prints WebSocket URL + port
# If port ≠ app config, update MSW_WS_URL (or VITE_MSW_WS_URL / NEXT_PUBLIC_MSW_WS_URL) to match output
msw-cli add "http.get('/api/users', () => HttpResponse.json([{ id: 1 }]))"
msw-cli status # connected must be true for mocks to apply
msw-cli close
Use msw-cli open --port 6789 when the app already hard-codes that port. list works without a session. Handler commands (add, update, remove, reset, status) require an open session for that cwd (or -s) — otherwise you get "Session not open".
Workflow
list/status— confirm no session is already open (or reuse it). Thenopenonly if needed — start daemon; read Port and WebSocket from markdown output.- Sync app — if port auto-changed (6789 busy), set
ws://127.0.0.1:<port>inMSW_WS_URL/VITE_MSW_WS_URL/NEXT_PUBLIC_MSW_WS_URLenv. add/update/remove/reset— handler changes.status— confirm browser connected.closewhen finished.
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.
- 1mo ago First seen · 90 lines · 41 tokens per session scan A 591308923094
msw-cli is a skill published in the GitHub repository JasonBoy/msw-mcp (81 stars, last pushed 4mo ago), licensed MIT. It adds 41 tokens to every session and 1,521 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
review-prs
Review a GitHub pull request in the googleapis/mcp-toolbox repo against the team's reviewer checklist: PR title/description conventions, linked issue, logic errors and unhandled edge cases, breaking changes, test coverage, docs updates, security (input handling), and new dependencies. Use whenever a maintainer asks…
bad-case-to-dpo
A guide to turning failed production agent runs into training and evaluation data. It explains how to find the first mistake, create preference examples for DPO (Direct Preference Optimization), and check that a fix does not damage other tasks.
eval-dataset-design
A guide to creating reliable test sets for AI agents. Each evaluation task includes the request, the simulated user's behaviour, a reset starting state, and a success check that can be independently verified.
omh-agent-evaluation
This is a Hermes-native agent-evaluation workflow skill.
llm-as-judge-evaluation
Evaluate LLM outputs using frontier models as judges. Use for pairwise model comparison, quality scoring with custom rubrics, and automated evaluation pipelines. Covers position bias mitigation, statistical significance, and generating preference data for DPO/RLHF.
golang-testing
Production-ready Golang tests — table-driven tests, testify suites and mocks, parallel tests, fuzzing, fixtures, goroutine leak detection with goleak, snapshot testing, code coverage, integration tests, idiomatic test naming. Use when writing or reviewing Go tests, choosing a testing approach, setting up Go test CI…