Bugfix
- 18 installs
- 22 repo stars
- Updated May 28, 2026
- acedergren/agentic-tools
bugfix is a Claude Code skill that autonomously diagnoses a bug's root cause from a report, failing test, or stack trace, implements a minimal fix, verifies it, and commits.
About
bugfix is a Claude Code skill that takes a bug report, failing test, stack trace, or CI failure and diagnoses the root cause, implements a minimal fix, verifies it, and commits. It classifies the root cause before writing code, collects evidence first, runs the targeted test and full workspace suite plus a typecheck, and stages only the files it changed. Developers use it to resolve a specific failing test or reported bug end to end.
- Autonomously diagnoses a bug's root cause from a report, failing test, or stack trace
- Implements a minimal fix, verifies with targeted and full test runs plus typecheck, then commits
- Classifies root cause (code, test, mock, type, import) before writing any code
Bugfix by the numbers
- 18 all-time installs (skills.sh)
- Ranked #403 of 596 Debugging skills by installs in the Skillselion catalog
- Data as of Jul 28, 2026 (Skillselion catalog sync)
bugfix capabilities & compatibility
- Capabilities
- bug diagnosis · root cause analysis · debugging · test fixing
- Use cases
- debugging · testing · code review
- Pricing
- Free
What bugfix says it does
Autonomous end-to-end bug fix: diagnose from evidence, find root cause, minimal fix, verify, commit.
Never refactor unrelated code while fixing a bug — scope creep breaks regression isolation.
State hypothesis explicitly before writing code: "The test fails because X, caused by Y."
npx skills add https://github.com/acedergren/agentic-tools --skill bugfixAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 18 |
|---|---|
| repo stars | ★ 22 |
| Last updated | May 28, 2026 |
| Repository | acedergren/agentic-tools ↗ |
What it does
Diagnose a failing test, stack trace, or bug report, implement a minimal fix, verify it, and commit.
Who is it for?
Resolving a specific failing test, stack trace, or CI failure end to end with a minimal, verified fix.
Skip if: Refactoring unrelated code or fixing other bugs noticed in passing; it warns against scope creep.
When should I use this skill?
You have a bug report, failing test, stack trace, or CI failure that needs diagnosis and repair.
What you get
A minimal fix with the failing test passing, the full suite green, typecheck clean, and a scoped commit.
- Minimal verified bug fix
- Scoped git commit with a fix(scope) message
By the numbers
- 5-row root-cause classification table
- 4-step verification sequence
- ships 2 scripts: collect-bugfix-context.sh, run-targeted-test.sh
Files
Bugfix
Autonomous end-to-end bug fix: diagnose from evidence, find root cause, minimal fix, verify, commit.
NEVER
- Never ask the user for more information unless the bug description is completely ambiguous — use tools to find it.
- Never refactor unrelated code while fixing a bug — scope creep breaks regression isolation.
- Never fix other bugs you notice while fixing the target — create a new task instead.
- Never
git add -A— stage only the files you changed. - Never skip running the full workspace test suite after a fix — targeted test passing doesn't mean no regression.
- Never commit until typecheck passes on the affected workspace.
Root Cause Classification (decide before writing any code)
| Type | Signal | Fix approach |
|---|---|---|
| Code bug | Logic error, wrong query, bad comparison | Fix implementation |
| Test bug | Expectation contradicts documented contract | Fix the test — explain why it was wrong |
| Mock wiring | mockReset: true pattern not followed, stale mock state | Use correct mock pattern from CLAUDE.md |
| Type error | TypeScript compilation failure | Fix types, not tests |
| Import error | Wrong package path, missing export | Fix import resolution |
If it's a mock wiring issue: read the mock patterns in CLAUDE.md before writing anything — there are three distinct patterns (forwarding, object-bag, counter-based sequencing).
Evidence-First Thinking
Collect before hypothesizing: 1. Run the failing test — see the exact error output, not just the description 2. Read the failing test — understand what it expects 3. Read the source under test 4. git log --oneline -10 -- <file> — was this recently changed? 5. For runtime errors: check logs, route/plugin/service code
State hypothesis explicitly before writing code: "The test fails because X, caused by Y."
Abort Conditions (stop and ask user)
- Bug is in security-sensitive area (auth, RBAC, IDOR) — confirm fix approach first
- Fix requires changing more than 5 files — may be an architectural issue
- Root cause requires changing the mock strategy for an entire test suite
Scripts
bash scripts/collect-bugfix-context.sh apps/api/src/tests/routes/auth.test.ts
bash scripts/run-targeted-test.sh apps/api/src/tests/routes/auth.test.ts
bash scripts/run-targeted-test.sh apps/api/src/tests/routes/auth.test.ts "returns 500"Verification Sequence
1. Run the specific failing test — must pass 2. Run the full workspace suite — no new failures 3. Run typecheck on the affected workspace (npx tsc --noEmit) 4. git diff --name-only — verify every changed file relates to the bug; revert anything that doesn't
Commit Format
fix(scope): what was broken and how it was fixed
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>Arguments
$ARGUMENTS: Error message, failing test path, CI log URL, or reproduction steps. If empty, ask for the error or failing test name.
#!/usr/bin/env bash
set -euo pipefail
TARGET="${1:-}"
if [ -z "$TARGET" ]; then
echo 'Usage: collect-bugfix-context.sh <test-file|source-file|search-term>' >&2
exit 1
fi
printf '## Bugfix Context\n\n'
echo '### Recent history'
git log --oneline -10 -- "$TARGET" 2>/dev/null || true
echo
echo '### Matching files'
rg -n "$TARGET" apps packages tests . -g '!**/node_modules/**' -g '!**/.git/**' || true
echo
echo '### Likely tests'
case "$TARGET" in
*.test.*|*.spec.*) echo "$TARGET" ;;
*)
base="${TARGET%.*}"
ls "${base}.test."* "${base}.spec."* 2>/dev/null || true
;;
esac
#!/usr/bin/env bash
set -euo pipefail
TARGET="${1:-}"
if [ -z "$TARGET" ]; then
echo 'Usage: run-targeted-test.sh <test-file> [test-name-pattern]' >&2
exit 1
fi
NAME_PATTERN="${2:-}"
if [ -n "$NAME_PATTERN" ]; then
npx vitest run "$TARGET" --reporter=verbose -t "$NAME_PATTERN"
else
npx vitest run "$TARGET" --reporter=verbose
fi
Related skills
Azure DiagnosticsSystematically diagnose and resolve production issues on Microsoft Azure using official Microsoft guidance.495k1.3kAzure MessagingQuickly diagnose and fix connection, authentication, and message-processing failures when using Azure Event Hubs or Service Bus SDKs.483k1.3k
Diagnosing BugsGet a systematic, step-by-step process that surfaces the real root cause instead of guessing at bugs.291k200k
Use My BrowserWhen their agent task requires access to the live browser session, rendered DOM state, authenticated dashboards, localhost apps, or DevTools-selected elements instea269k71
Systematic DebuggingFollow a repeatable four-phase process that forces root-cause discovery before any code changes.210k265k
Safe DebugGet conservative, non-destructive diagnosis of deep learning and agent errors before any code changes are made.185k512FAQ
How does it avoid regressions?
It runs the specific failing test, then the full workspace suite, then a typecheck, and reverts any changed file that does not relate to the bug.
Will it fix other bugs it notices?
No. It creates a new task instead and never refactors unrelated code, to keep regression isolation intact.