fix-bug

A disciplined workflow for fixing one software bug from a small reproducer through a tested change and one commit. A reproducer is the smallest input or test that shows the wrong behavior.

In plain words
What is it for?
Use it to reproduce a crash or incorrect result, write a failing regression test, identify the underlying cause, implement the fix, and verify it.
Why use it?
It prevents fixes based on guesses and preserves proof that the bug failed before the change and passed afterward.

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/leifericf/agentic-sdk/fix-bug
Any agent
npx skills add leifericf/agentic-sdk --skill fix-bug
Clone the repo
git clone --depth 1 https://github.com/leifericf/agentic-sdk

Made for: Claude Code, Codex.

Per session 17 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 794 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00017 $0.00794
Opus 5 $0.00009 $0.00397
Sonnet 5 $0.00003 $0.00159
Haiku 4.5 $0.00002 $0.00079

Measured 2d ago against content hash f77c0ad582f1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

fix-bug 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 2d 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.

skills/fix-bug/SKILL.md · 73 lines

How it starts

The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.

fix-bug

Role: the single-bug fix. Reproduces the bug, writes the failing test, fixes at the source, verifies, lands one commit.

Prerequisites

~/.agentic-sdk/<project>/project.edn exists with :lanes. A bug report: a wrong behavior, a crash on a specific input, a failing assertion, or a description.

Procedure

The discipline, in order. Do not skip steps.

  1. Reproduce. Reduce to the smallest form that shows the wrong behavior: a single function call, a one-input test, a minimal fixture through the failing path. No fix lands without a confirmed reproducer. "Cannot reproduce" goes back to the reporter with what you tried. Keep reproducer fixtures under the project's test fixtures path and cite it in the regression test.
  2. Failing test first. Write the regression test in the right surface via write-tests: pure core to the core test namespace, a native edge to a round-trip integration test, persistence to a scratch store. Run it; watch it fail for the expected reason. Commit it first (Tests: ...) so history proves fail then pass.
  3. Find the cause, not the symptom. Check the decision index (the ADR store from the descriptor) and the design docs first. Behavior that matches an existing ADR or documented design choice is not a bug; report that back instead of fixing it. Then fix at the source: the pure core function, the native body, the persistence transaction, or the shell wiring. Never a caller-side special case, never a test adjustment. Classify the gap: a real defect (fix here), an upstream platform difference (document at the site), or harness debt (fix the harness).
  4. Fix smallest-sufficient. If the cause is in another module than expected, follow it and say so. A factoring finding is a valid fix-bug outcome: open it as a forward task, do not silently refactor here.
  5. Verify. Dispatch one verifier running verify-lanes against the project's lanes (from the descriptor): the cheap tier always. When the fix touched a native edge (any native body or the boundary itself), also a round-trip test that compiles and calls the real native code, and the native formatter on changed source. When the fix touched persistence, a transaction-history test. When the fix touched a computation with tolerance, an assertion that returned values are within tolerance on a known-good fixture.
  6. Commit. One commit via write-commit: Category: Imperative subject, single line. The regression test and the fix land as the next commit on the tip, not a branch.

Read the full file on GitHub · 73 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. 2d ago First seen · 73 lines · 17 tokens per session scan A f77c0ad582f1

Subscribe to this mod's changes

fix-bug is a skill published in the GitHub repository leifericf/agentic-sdk (5 stars, last pushed 13d ago), licensed MIT. It adds 17 tokens to every session and 794 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

agent-host-chat-contributions

Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.

microsoft/vscode · 56 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens