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 DDS-Solutions/AI-TadPole-OS --skill systematic-debugginggit clone --depth 1 https://github.com/DDS-Solutions/AI-TadPole-OSWrote 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/dds-solutions/ai-tadpole-os/systematic-debugging)<a href="https://agentmods.dev/skills/dds-solutions/ai-tadpole-os/systematic-debugging"><img src="https://agentmods.dev/badge/skills/dds-solutions/ai-tadpole-os/systematic-debugging.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00025 | $0.00981 |
| Opus 5 | $0.00013 | $0.00491 |
| Sonnet 5 | $0.00005 | $0.00196 |
| Haiku 4.5 | $0.00003 | $0.00098 |
Grade A, and why
systematic-debugging 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 4d 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 — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
[!IMPORTANT] AI Context & Knowledge Heritage
- Subsystem: Agent Skills Registry / systematic-debugging
- Architecture:
@docs ARCHITECTURE:Documentation- Failure Path: Information drift, legacy terminology, or documentation mismatch.
- Observability: Traceability via
execution/parity_guard.py([SKILL])
Systematic Debugging
Source: obra/superpowers
Overview
This skill provides a structured approach to debugging that prevents random guessing and ensures problems are properly understood before solving.
4-Phase Debugging Process
Phase 1: Reproduce & Tighten Feedback Loop
🛑 STRICT GATE: Do NOT touch code or hypothesize fixes until a tight, red-capable reproduction command is built and verified.
Build the tightest possible feedback loop in roughly this order:
- Failing test (unit, integration, e2e) asserting the exact symptom.
- Curl / HTTP script against a local endpoint.
- CLI invocation diffing stdout/stderr against expected fixture.
- Captured trace / payload replay through isolated code path.
Feedback Loop Quality Criteria
- Red-Capable: Drives the actual bug code path and fails on the user's exact symptom (not just "didn't crash").
- Deterministic: Returns identical pass/fail verdict on 100% of runs (for flaky bugs, loop 100x to raise repro rate).
- Fast: Completes in < 2 seconds.
## Reproduction Gate Sign-off
- Command Executed: `<exact command line>`
- Output Log: `<pasted red failure log>`
- Loop Duration: `<seconds>`
Phase 2: Isolate & Discriminative Probe
Narrow down the source using evidence and active hypothesis discrimination (Schema Harness protocol).
## Isolation & Discriminative Probing
- When did this start happening?
- What changed recently?
- Does it happen in all environments?
### Hypothesis Discrimination (Probing Protocol)
Formulate two competing hypotheses and design an active probe:
- **Hypothesis A (H_A)**: [Proposed cause A] -> Expected probe outcome: [Outcome A]
- **Hypothesis B (H_B)**: [Proposed cause B] -> Expected probe outcome: [Outcome B]
- **Discriminative Probe Execution**: Execute non-destructive test to falsify one hypothesis.
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.
- 4d ago First seen · 127 lines · 25 tokens per session scan A 4e1aea15c230
systematic-debugging is a skill published in the GitHub repository DDS-Solutions/AI-TadPole-OS (8 stars, last pushed 2d ago), licensed MIT. It adds 25 tokens to every session and 981 once invoked, about $0.0001 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
test-electron-app
Drive the real running PostHog Electron app (live tRPC, workspace-server, real data) over CDP with agent-browser. Connect to the running app on port 9222, test desktop changes against a local Django stack, snapshot the accessibility tree, inspect network requests, and screenshot only when explicitly asked. Use when…
verify-bug
Post-merge UAT verification workflow. Walks JIRA reproduce steps, performs comparative audits (Before/After), attaches evidence to JIRA, and transitions status on PASS.
handle-regression
Protocol for detecting, isolating, and fixing regressions in test262 pass count. Use when a test run shows fewer passes than expected.
tuturuuu-e2e-auth-debugging
Diagnose Tuturuuu local E2E authentication, dev-session, and onboarding failures.
debug-and-test
Use when debugging or validating an Air Jam project so diagnostics, logging, and tests stay intentional, structured, and aligned with the project architecture.
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…