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/aegntic/compound-engineering/systematic-debuggingnpx skills add aegntic/compound-engineering --skill systematic-debugginggit clone --depth 1 https://github.com/aegntic/compound-engineeringWhat 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 | $0.00025 | $0.01340 |
| Opus 5 | $0.00013 | $0.00670 |
| Sonnet 5 | $0.00005 | $0.00268 |
| Haiku 4.5 | $0.00003 | $0.00134 |
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 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.
How it starts
The opening of the file, as written. The whole thing — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Systematic Debugging
A structured methodology for debugging unexpected errors encountered during implementation. Prevents trial-and-error guessing by enforcing a disciplined observe-hypothesize-test-fix cycle.
Announce at start: "I'm using the systematic-debugging skill to diagnose this issue."
When to Use
- A test fails unexpectedly during implementation
- An error occurs that you did not anticipate
- A subagent has retried 2+ times without success
- Something "should work" but does not
- You are tempted to make random changes hoping something fixes it
When NOT to Use
- The error message is clear and the fix is obvious (just fix it)
- You are validating a reported bug (use the
bug-reproduction-validatoragent instead) - The failure is a known issue documented in
docs/solutions/
The 4-Phase Process
Phase 1: Observe
Gather evidence before forming any theories. Do not skip this phase.
- Reproduce the error -- Run the exact command that failed. Confirm you see the same error.
- Read the full error -- Read the COMPLETE error message, stack trace, and any surrounding output. Do not skim.
- Check the context -- What changed recently? What was the last thing that worked? What is different now?
- Gather state -- Check relevant logs, database state, environment variables, configuration files, or any other state that could be relevant.
- Note the symptoms -- Write down exactly what you observe:
- What happens (the error)
- What should happen (expected behavior)
- When it happens (always, sometimes, under specific conditions)
Output of Phase 1: A clear, factual description of the symptoms with no theories attached.
Phase 2: Hypothesize
Form structured theories about the root cause. Do not jump to fixing yet.
- List 3 possible root causes ranked by likelihood:
- Most likely: [hypothesis based on error message and context]
- Possible: [alternative explanation]
- Less likely but worth checking: [edge case or environmental cause]
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 · 141 lines · 25 tokens per session scan A ca3110e4660a
systematic-debugging is a skill published in the GitHub repository aegntic/compound-engineering (2 stars, last pushed 2mo ago), licensed MIT. It adds 25 tokens to every session and 1,340 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 2026-08-31.
Other skills, from other repositories
a2ui-renderer
Render A2UI (Agent-to-UI declarative surfaces) in CopilotKit v2. Enable the runtime via CopilotRuntime({ a2ui: {...} }), then enable the provider via . Auto-activates via /info — do NOT manually pass renderActivityMessages. createA2UIMessageRenderer ships from @copilotkit/react-core/v2; low-level primitives…
copilotkit-develop
Use when building AI-powered features with CopilotKit v2 -- adding chat interfaces, registering frontend tools, sharing application context with agents, handling agent interrupts, and working with the CopilotKit runtime.
copilotkit-integrations
Use when wiring an external agent framework (LangGraph, CrewAI, PydanticAI, Mastra, ADK, LlamaIndex, Agno, Strands, Microsoft Agent Framework, or others) into a CopilotKit application via the AG-UI protocol.
copilotkit-debug
Use when diagnosing CopilotKit issues -- runtime connectivity failures, agent not responding, streaming errors, tool execution problems, transcription failures, version mismatches, and AG-UI event tracing.
channels-setup
Use when a developer wants to build their first CopilotKit Channels agent and get it answering in Slack or Microsoft Teams — "set up a channel", "connect my agent to Slack", "get my agent into Teams", or starting from nothing and wanting a working channel end to end. Covers the whole path: inspecting or scaffolding…
fixer
Surgical code fixer for Bug Hunter. Implements minimal, precise fixes for verified bugs. Uses doc-lookup (Context Hub + Context7) to verify correct API usage in patches. Respects fix strategy classifications (safe-autofix vs manual-review vs larger-refactor).