Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add navapbc/digital-service-orchestra/plugin install dsoWrote 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/navapbc/digital-service-orchestra/playwright-debug)<a href="https://agentmods.dev/skills/navapbc/digital-service-orchestra/playwright-debug"><img src="https://agentmods.dev/badge/skills/navapbc/digital-service-orchestra/playwright-debug/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/navapbc/digital-service-orchestra/playwright-debug"><img src="https://agentmods.dev/badge/skills/navapbc/digital-service-orchestra/playwright-debug.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00155 | $0.04987 |
| Opus 5 | $0.00077 | $0.02493 |
| Sonnet 5 | $0.00031 | $0.00997 |
| Haiku 4.5 | $0.00015 | $0.00499 |
Grade A, and why
playwright-debug scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 465 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Playwright Debug: 3-Tier Hypothesis-First Process
Structured browser debugging that reduces @playwright/cli token usage by 4x by generating hypotheses from code before opening a browser.
Token cost reference: Full CLI session ~114k tokens. Targeted
@playwright/cli run-codecall ~8-12k tokens. Code-only analysis ~2-4k tokens. Resolve at the cheapest tier possible.
Pre-flight: @playwright/cli Availability Check
Before starting any browser debugging, verify the CLI binary is available:
# Resolve the direct binary path (avoid npx stdout pollution)
PW_CLI="$(npm root)/.bin/playwright"
if [[ ! -x "$PW_CLI" ]]; then
PW_CLI="$(command -v playwright 2>/dev/null || true)"
fi
if [[ -z "$PW_CLI" || ! -x "$PW_CLI" ]]; then
echo "ERROR: @playwright/cli binary not found. Install with: npm install @playwright/cli"
echo "Cannot proceed with browser debugging."
exit 1
fi
# Verify version
"$PW_CLI" --version
If the binary is not available, do NOT proceed with Tier 2 or Tier 3. Remain in Tier 1 (code analysis only) and report the missing dependency.
Project-Specific Reference (one-time setup)
Many sections below augment the generic guidance with project-specific data (symptom-to-code-path table, framework constraints, worked examples) loaded from a single reference file. Resolve it once at session start:
PLAYWRIGHT_DEBUG_REF=$(bash ".claude/scripts/dso read-config.sh" skills.playwright_debug_reference 2>/dev/null || echo "")
When a section below says "PROJECT-SPECIFIC: read the ## <section name> section from $PLAYWRIGHT_DEBUG_REF", do that lookup if $PLAYWRIGHT_DEBUG_REF is non-empty; skip the section augment if empty.
Session Management
Use a unique session name incorporating the worktree identifier to avoid collisions across concurrent worktrees:
WORKTREE_ID="$(basename "$(git rev-parse --show-toplevel)")"
SESSION_NAME="pw-debug-${WORKTREE_ID}"
All CLI commands below use -s=$SESSION_NAME for session persistence. Open the session once before Tier 2, and register a cleanup trap to ensure the session is closed even if the agent is interrupted:
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.
- 6d ago First seen · 465 lines · 155 tokens per session scan A 15a7f1b6db42
playwright-debug is a skill published in the GitHub repository navapbc/digital-service-orchestra (6 stars, last pushed yesterday), licensed Apache-2.0. It adds 155 tokens to every session and 4,987 once invoked, about $0.0008 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
chrome-devtools-cli
Use this skill to write shell scripts or run shell commands to automate tasks in the browser or otherwise use Chrome DevTools via CLI.
a11y-debugging
Uses Chrome DevTools MCP for accessibility (a11y) debugging and auditing based on web.dev guidelines. Use when testing semantic HTML, ARIA labels, focus states, keyboard navigation, tap targets, and color contrast.
chrome-devtools
Uses Chrome DevTools via MCP for efficient debugging, troubleshooting and browser automation. Use when debugging web pages, automating browser interactions, analyzing performance, or inspecting network requests. This skill does not apply to --slim mode (MCP configuration).
chrome-performance-optimizer
Autonomous multi-agent performance optimization loop for Chromium and V8. Supports profile-seeded mode (analyzing Speedometer 3 / JetStream profiles via pprof or Sagacity MCP) and pattern-driven discovery mode (fan-out exploration of Blink and V8 macro-patterns grounded in historical wins and past rejected CLs).…
nullaway
Guide for resolving NullAway static analysis errors. Best practices for: Passing ObservableSupplier/Supplier Dereferencing potentially @Nullable values Adding @NullMarked to Java code.
bisect
Bisect regressions or broken builds in the Chromium repository using deterministic binary search, checking out midpoint commits, syncing dependencies with gclient sync, compiling the target with autoninja, and querying the user for test results until the culprit commit is isolated.