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 commands/lab94/frenchie-skill/systematic-debuggit clone --depth 1 https://github.com/Lab94/frenchie-skillWhat 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 | $0.00000 | $0.00296 |
| Opus 5 | $0.00000 | $0.00148 |
| Sonnet 5 | $0.00000 | $0.00059 |
| Haiku 4.5 | $0.00000 | $0.00030 |
Grade A, and why
systematic-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 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
/systematic-debug
Debug by evidence, not guesswork.
Capture reproduction steps, expected vs actual behavior, observations, hypotheses, narrowing strategy, root cause, fix plan, and regression validation. Use logs/tests/tools to eliminate possibilities before changing code.
Aliases: /debug, /fix-bug, /frenchie-systematic-debug.
Workflow
Evidence
Collect exact error output, logs, screenshots, request/response samples, failing test output, environment details, and recent changes. Separate observed facts from assumptions.
Reproduction
Write the shortest reliable reproduction path. Include setup, command/input, expected behavior, actual behavior, and whether the issue reproduces on main/current branch.
Hypotheses
List plausible causes with confidence and the observation that would prove or disprove each one. Do not patch before at least one hypothesis has supporting evidence.
Narrowing Strategy
Use targeted tests, logging, bisecting, controlled input changes, dependency isolation, or minimal reproduction to eliminate causes. Prefer the cheapest experiment that can falsify a hypothesis.
Root Cause
State the actual mechanism, affected code path, why existing tests missed it, and why the issue appeared now.
Fix Plan
Describe the smallest safe change, files likely touched, required tests, rollback, and risk. Ask before widening scope.
Regression Validation
Add or update regression tests when feasible. Record commands, manual checks, and any residual risk in 06-test-report.md.
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 · 38 lines · 0 tokens per session scan A 61d89a437725
systematic-debug is a command published in the GitHub repository Lab94/frenchie-skill (0 stars, last pushed 3mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 296 tokens. 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 commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.