systematic-debugging

A step-by-step debugging method: observe the failure, form hypotheses, run experiments, eliminate causes, and confirm the root cause. It requires reproducing and verifying the problem before fixing it.

In plain words
What is it for?
Use it to reproduce bugs, collect errors and logs, test possible causes, find the smallest failing case, and verify the fix.
Why use it?
It reduces guesswork by using evidence and small experiments to identify why a bug occurs.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/anentrypoint/freddie/systematic-debugging
Any agent
npx skills add AnEntrypoint/freddie --skill systematic-debugging
Clone the repo
git clone --depth 1 https://github.com/AnEntrypoint/freddie

Made for: Claude Code, Codex.

Per session 21 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 691 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00021 $0.00691
Opus 5 $0.00010 $0.00345
Sonnet 5 $0.00004 $0.00138
Haiku 4.5 $0.00002 $0.00069

Measured yesterday against content hash 557d6fcf83f9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

systematic-debugging scanned grade A with 1 finding 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

| Network issue | tcpdump, curl -v |
skills/software-development/systematic-debugging/SKILL.md · 81 lines

How it starts

The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Systematic Debugging

Do not guess. Form hypotheses, design experiments, eliminate candidates, converge on root cause through observation.

The debugging loop

OBSERVE → HYPOTHESISE → EXPERIMENT → ELIMINATE → CONVERGE

Never skip to EXPERIMENT without OBSERVE. Never fix without CONVERGE.

Phase 1: OBSERVE — reproduce the bug

  1. Write a reproduction recipe — exact steps, inputs, environment.
  2. Confirm deterministic (always fails) vs intermittent (% failure rate).
  3. Find the smallest reproduction — strip everything not needed to trigger the bug.
  4. Capture: error message, stack trace, logs, HTTP request/response, query.

Phase 2: HYPOTHESISE — list candidate causes

Write every possible cause. Rank by:

  • Proximity to the failure point
  • Recent changes (last deploy, last config change)
  • Complexity (more complex code = more places to hide bugs)

Phase 3: EXPERIMENT — test one hypothesis at a time

Hypothesis: Redis is evicting sessions under memory pressure
Experiment: redis-cli INFO memory | grep used_memory_human; redis-cli MONITOR | grep DEL
Expected if TRUE: memory near maxmemory, DEL commands on session keys
Expected if FALSE: memory headroom, no unexpected DELs
Result: ...

Never change two things at once. One variable per experiment.

Phase 4: ELIMINATE — cross off falsified hypotheses

  • FALSIFIED — evidence rules it out
  • CONFIRMED — evidence supports it
  • INCONCLUSIVE — need more data

Stop when exactly one hypothesis is CONFIRMED and all others FALSIFIED.

Phase 5: CONVERGE — fix at root cause

  1. Write a failing test that reproduces the bug.
  2. Implement the fix.
  3. Confirm the test now passes.
  4. Check for similar bugs in adjacent code.

Debugging tools

Situation Tool
Slow code path Profiler (node --prof, py-spy)
Memory leak Heap snapshot (Chrome DevTools)
Network issue tcpdump, curl -v
DB slow query EXPLAIN ANALYZE
Race condition Thread sanitiser, stress test
Intermittent failure Log correlation by request ID

Read the full file on GitHub · 81 lines

Changes

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.

  1. yesterday First seen · 81 lines · 21 tokens per session scan A 557d6fcf83f9

Subscribe to this mod's changes

systematic-debugging is a skill published in the GitHub repository AnEntrypoint/freddie (5 stars, last pushed 2d ago), licensed MIT. It adds 21 tokens to every session and 691 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

itchio-new-game-hunt

Hunt for fresh browser-playable games on itch.io /newest that are worth building SEO arbitrage sites for. Crawls new releases, scores them by signals, produces ranked shortlist.

kennyzir/7deer_skills · 45 tokens

arch-save

Save an architect's state, clear its context, and re-init automatically — the packaged save→clear→re-init refresh cycle. Use when the owner directs a context refresh, or says "/arch-save", "save and clear", "refresh your context". Runs on the owner's direction; an architect does not invoke it autonomously mid-task.…

cluesmith/codev · 86 tokens

arch-init

Adopt an architect identity and recover its state from codev/state/ .md. Use when an architect terminal needs to (re)establish which architect it is — after a restart, context loss, or session handoff — or when the user says "/arch-init", "you are the X architect", or "recover your architect state". Identity resolves…

cluesmith/codev · 99 tokens

runnable-worktrees

Make builder worktrees runnable — the .codev/config.json worktree block (symlinks, postSpawn, devCommand), the afx dev CLI, VSCode dev controls, and per-stack config recipes. Use when configuring a repo so reviewers can run a builder's branch, when afx dev fails to bind or start, when a dev process is orphaned holding…

cluesmith/codev · 102 tokens

codev

Codev project management CLI — init, adopt, update, and doctor commands. Check this skill before running any codev command (except consult, porch, or afx which have their own skills). Use when setting up new projects, adding codev to existing repos, updating framework files, or diagnosing missing dependencies.

cluesmith/codev · 72 tokens

porch

Protocol orchestrator CLI — drives SPIR, ASPIR, AIR, TICK, and BUGFIX protocols via a state machine. ALWAYS check this skill before running any porch command. Use when you need to check project status, approve gates, signal phase completion, or manage protocol state. Also use when a builder asks about gate approvals…

cluesmith/codev · 76 tokens