fix-bug

A step-by-step procedure for fixing a reported software bug. It requires reproducing the problem, writing a test that fails before the fix, finding the root cause, making a small change, and verifying the result.

In plain words
What is it for?
Use it to investigate bugs, protect sensitive files that need approval, run the relevant tests, request a code review, and record the work.
Why use it?
It prevents fixes based only on symptoms and leaves a regression test so the same bug is less likely to return.

Cursor rule for Cursor

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 rules/kunalsuri/ai-fication-kit/fix-bug
Clone the repo
git clone --depth 1 https://github.com/kunalsuri/ai-fication-kit

Made for: Cursor.

Per session 27 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 381 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 $0.00027 $0.00381
Opus 5 $0.00014 $0.00191
Sonnet 5 $0.00005 $0.00076
Haiku 4.5 $0.00003 $0.00038

Measured 2d ago against content hash 9596ea536055, 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.

.cursor/rules/fix-bug.mdc · 26 lines

What it actually says

Fix the reported bug following the fix-bug skill contract (VS Code auto-discovers it from .claude/skills/fix-bug/ or .agents/skills/fix-bug/ in this repo). Summary of the contract:

  1. Reproduce first. Draft ai/lab/specs/BUGFIX_<name>.md from the template (symptom, exact steps) and get the user's OK before touching code.
  2. Failing test before fix. Turn the reproduction into a permanent regression test and watch it fail — that is the proof the bug is understood.
  3. Locate via the maps. MODULE_MAP Stability → FEATURE_MAP gotchas → WORKLOG history (was this area just touched? is the behavior deliberate?).
  4. Respect Stability. Root cause in frozen or ? files ⇒ explicit human approval in this conversation, recorded in the bugfix doc.
  5. Root cause, then surgical fix. Name the defect, not the symptom; smallest diff that turns the regression test green. No drive-by refactors.
  6. Verify. Regression test green plus the suites covering the touched area. Failing or unrun tests ⇒ not fixed.
  7. Review & record. Request /review-change on the diff; append the bugfix row to ai/lab/WORKLOG.md and the FEATURE_MAP gotcha — all tagged [inferred] for the human to verify.
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 · 26 lines · 27 tokens per session scan A 9596ea536055

Subscribe to this mod's changes

fix-bug is a cursor rule published in the GitHub repository kunalsuri/ai-fication-kit (3 stars, last pushed 3d ago), licensed Apache-2.0. It adds 27 tokens to every session and 381 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.