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.
git clone --depth 1 https://github.com/vypdev/copilotWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/rules/vypdev/copilot/bugbot)<a href="https://agentmods.dev/rules/vypdev/copilot/bugbot"><img src="https://agentmods.dev/badge/rules/vypdev/copilot/bugbot/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/rules/vypdev/copilot/bugbot"><img src="https://agentmods.dev/badge/rules/vypdev/copilot/bugbot.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00008 | $0.00310 |
| Opus 5.5 | $0.00003 | $0.00124 |
| Sonnet 5.5 | $0.00002 | $0.00062 |
| Haiku 4.5 | $0.00001 | $0.00031 |
Grade A, and why
bugbot 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 1mo 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.
What it actually says
Bugbot technical reference
Read _agent/docs/bugbot.md and the public /bugbot documentation before
changing Bugbot. The implementation lives under
src/application/usecases/steps/commit/bugbot/; provider implementations stay
behind semantic application ports.
Current invariants:
- Review and intent tasks are read-only; fixer tasks may mutate only after application authorization.
- Every structured response is validated locally, regardless of CLI-native schema support.
- One canonical PR diff snapshot supplies files, patches, and addressable locations for a run.
- Finding markers require both a local fingerprint and a semantic fingerprint. Marker authorship must match the authenticated workflow identity.
- Publication revalidates the PR head and uses one native review with line, range, or file-level child comments.
- Autofix verification and commit success do not resolve findings; a fresh independent review must verify resolution.
- Canonical comment options are
dry-run,trace-rules, andsuggested-changes. - Canonical mutation/review commands are parsed by
src/domain/bugbot/review_command.tsandsrc/domain/copilot_command.ts; do not add unversioned aliases.
Use the source types and policies as the executable contract. Do not restore an older marker shape, direct-diff reader, provider-specific application path, or alternate command spelling.
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.
- 1mo ago Changed · -94 lines · -17 tokens per session f1f136a64ad6
- 1mo ago Changed · +1 lines 160cc131259b
- 1mo ago First seen · 129 lines · 25 tokens per session scan A b74d0f21f198
bugbot is a cursor rule published in the GitHub repository vypdev/copilot (3 stars, last pushed today), licensed MIT. It adds 8 tokens to every session and 310 once invoked, about $0.0000 per session on Opus 5.5. 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.
Other cursor rules, from other repositories
refactor-cleaner
Dead code cleanup and consolidation specialist. Use PROACTIVELY for removing unused code, duplicates, and refactoring. Runs analysis tools (knip, depcheck, ts-prune) to identify dead code and safely removes it.
techdebt
Find and eliminate technical debt across the whole codebase — duplicated code, dead code, redundant abstractions.
code-change-refactor
This rule applies when refactoring existing code to improve quality, adopt new patterns, or integrate with newly created functionality.
validator_quality
Quality Validator — check for complexity, dead code, inconsistent naming, and technical debt.
201-bugbot-autofix
200: Responding to BugBot PR comments.
ponytail
Ponytail, lazy senior dev mode. Always pick the simplest solution that works.