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/jmsa/argus/debug-sessionnpx skills add Jmsa/argus --skill debug-sessiongit clone --depth 1 https://github.com/Jmsa/argusWhat 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 | $0.00040 | $0.00450 |
| Opus 5 | $0.00020 | $0.00225 |
| Sonnet 5 | $0.00008 | $0.00090 |
| Haiku 4.5 | $0.00004 | $0.00045 |
Grade A, and why
debug-session 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.
What it actually says
Capture a complete debugging snapshot of $ARGUMENTS using the Argus MCP tools.
Steps
-
Launch Chrome (skip if already connected)
browser_launch -
Open the target URL
tab_open { url: "$ARGUMENTS" } → note the returned targetId -
Start recording
console_start { targetId } network_start_recording { targetId } -
Trigger the behaviour to debug
- Use
tab_navigateto navigate to a specific path - Use
page_evaluateto run arbitrary JS (e.g. click buttons, trigger events) - Wait for async operations as needed
- Use
-
Capture evidence
console_get_logs { targetId } ← all logs console_get_logs { targetId, type: "error" } ← errors only network_get_requests { targetId } ← all requests network_get_requests { targetId, hasError: true } ← failed requests tab_screenshot { targetId, fullPage: true } ← full page PNG -
Summarise findings — report:
- Any console errors or warnings
- Any failed or slow network requests
- What the screenshot shows
- Recommended next steps
-
Iterate if needed
- Fix issues found in the logs
- Use
page_reloadto test the fix - Repeat from step 5
Tips
- Combine
console_get_logs { type: "error" }withnetwork_get_requests { hasError: true }to quickly triage failures. page_evaluatecan inject scripts, read DOM state, or simulate user interactions.- Screenshots are returned as base64 PNG and displayed inline in supported MCP clients.
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 · 58 lines · 40 tokens per session scan A 34981f4aa99f
debug-session is a skill published in the GitHub repository Jmsa/argus (0 stars, last pushed 5mo ago), licensed MIT. It adds 40 tokens to every session and 450 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
opencli-usage
Use at the start of any OpenCLI session — this is the top-level map of what opencli can do, how to discover adapters, what flags and output formats are universal, and which specialized skill to load next. Point here when an agent asks "what can opencli do?" or "how do I find the right command?".
opencli-sitemap-author
Use when creating or maintaining OpenCLI site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge for a website. Use after browser exploration discovers durable site context, when a sitemap is stale, or when promoting local site knowledge into the repo.
opencli-browser-sitemap
Use when driving a website with opencli browser and sitemap context is available, requested, or needed to avoid blind navigation. Guides agents to consume site sitemap files lazily, choose adapter/browser fallback paths, resume from state signatures, and mark stale sitemap entries without trusting them over live…
pinchtab-mcp
Use this skill when a task requires browser automation through PinchTab's MCP server connected to a remote browser instance. Covers navigation, element interaction, data extraction, form filling, multi-step flows, and session management via MCP tools.
pinchtab-stealth-score
Run the PinchTab stealth-score sweep against 15 bot-detection / fingerprint sites (sannysoft, rebrowser, deviceandbrowserinfo, iphey, whoer, browserscan, pixelscan, fingerprint-scan, incolumitas, fvision, amiunique, browserleaks, creepjs, coveryourtracks, fingerprint-demo). Starts a Docker PinchTab container per…
openbot-data-access
Governs how the OpenBot browser app reads and writes server data — every request goes through client in app/src/lib/client.ts, every read is a queryOptions factory in app/src/lib/ /queries.ts, every write is a mutationOptions factory in app/src/lib/ /mutations.ts, and components consume them through…