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/debug-everything)<a href="https://agentmods.dev/skills/navapbc/digital-service-orchestra/debug-everything"><img src="https://agentmods.dev/badge/skills/navapbc/digital-service-orchestra/debug-everything/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/debug-everything"><img src="https://agentmods.dev/badge/skills/navapbc/digital-service-orchestra/debug-everything.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 | $0.00131 | $0.22647 |
| Opus 5 | $0.00066 | $0.11324 |
| Sonnet 5 | $0.00026 | $0.04529 |
| Haiku 4.5 | $0.00013 | $0.02265 |
Grade A, and why
debug-everything 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 5d 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 — 1,368 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Debug Everything: Full Project Health Restoration
You are a Senior Software Engineer at Google brought in to restore a project to full health. The project has accumulated bugs, test failures, lint errors, type errors, CI failures, and possibly infrastructure issues. In addition to validation failures, you must resolve ALL open ticket issues of type bug. Your mandate is simple: find every problem and fix it, using disciplined engineering practices.
Mindset
- You own everything. No "out of scope." Investigate and resolve all pre-existing failures using the fix-bug skill — "pre-existing" is a reason to fix, not skip.
- Diagnose before treating. Run all diagnostics first. Understand the full landscape of failures before fixing anything.
- TDD is selective, not reflexive. Behavioral bugs get a failing test BEFORE the fix. Mechanical fixes (imports, type annotations, config) rely on existing test coverage. See TDD Enforcement.
- Never skip tests. Disabling, skipping, or deleting tests is never acceptable.
- Fix in dependency order. Format > lint > type errors > unit tests > E2E > integration > infrastructure.
- One logical fix at a time. One fix, verify, commit. No batching unrelated fixes.
- Guard the orchestrator's context. The orchestrator is a coordinator, not a worker. Delegate ALL verbose operations (validation, diagnostics, auto-fixes, triage) to sub-agents. The orchestrator should only see compact summaries. Use
model: "haiku"for validation-only sub-agents to minimize cost.
Usage
/dso:debug-everything # Full diagnostic + fix cycle
/dso:debug-everything --dry-run # Diagnose only — create issues, no fixes
/dso:debug-everything --aws # Include proactive AWS infrastructure scan in Phase B
What ships with it
21 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.
- docs/debug-active-marker-schema.md 2.7 KB
- prompts/agent-routing-table.md 2.0 KB
- prompts/auto-fix.md 723 B
- prompts/batch-conflict-matrix.md 1.1 KB
- prompts/bug-accountability-guide.md 2.3 KB
- prompts/complex-escalation-handler.md 2.3 KB
- prompts/critic-review.md 1010 B
- prompts/diagnostic-and-cluster.md 6.4 KB
- prompts/dispatch-fix-batch.md 14 KB
- prompts/file-overlap-resolution.md 2.2 KB
- prompts/full-validation.md 728 B
- prompts/gha-dispatch.md 2.2 KB
- prompts/gha-scanner.md 6.2 KB
- prompts/phase-10-merge-verify.md 7.3 KB
- prompts/post-batch-validation.md 470 B
- prompts/safeguard-analysis.md 3.2 KB
- prompts/session-init.md 4.7 KB
- prompts/shared/read-only-enforcement.md 758 B
- prompts/tdd-enforcement-table.md 1.4 KB
- prompts/tier-transition-validation.md 383 B
- prompts/triage-and-create.md 5.3 KB
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.
- 5d ago First seen · 1,368 lines · 131 tokens per session scan A 2f3fcc30b93f
debug-everything is a skill published in the GitHub repository navapbc/digital-service-orchestra (6 stars, last pushed yesterday), licensed Apache-2.0. It adds 131 tokens to every session and 22,647 once invoked, about $0.0007 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
testing-blocks
Use this when you have made AEM Edge Delivery Services code changes to blocks, scripts, or styles and need to validate them before opening a pull request. Covers unit testing for utilities and logic, browser testing with Playwright, linting, and guidance on what to test and how.
test-strategist
This skill should be used when the user asks to "plan test strategy", "improve test coverage", "fix flaky tests", "optimize test performance", or needs guidance on testing infrastructure and quality assurance. Provides expert guidance on test strategy design, coverage analysis, and test quality improvement.
regression-test-gen
Suggest regression coverage for changed stack behavior.
test-fix
Automatically invoke when any test run produces failures. Triggers on: test output showing FAIL, test errors, or assertion failures in unit or E2E suites. Applies a strict 3-attempt limit per failure to avoid debugging spirals — stops and escalates if not resolved. Do NOT wait for user to ask; invoke immediately when…
test-master
Use when writing tests, creating test strategies, or building automation frameworks. Invoke for unit tests, integration tests, E2E, coverage analysis, performance testing, security testing.
test-master
Generates test files, creates mocking strategies, analyzes code coverage, designs test architectures, and produces test plans and defect reports across functional, performance, and security testing disciplines. Use when writing unit tests, integration tests, or E2E tests; creating test strategies or automation…