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.
npx agentmods add agents/guild-agents/guild/bugfixgit clone --depth 1 https://github.com/Guild-Agents/guildWhat 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 | $0.00007 | $0.00424 |
| Opus 5 | $0.00003 | $0.00212 |
| Sonnet 5 | $0.00001 | $0.00085 |
| Haiku 4.5 | $0.00001 | $0.00042 |
Grade A, and why
bugfix 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 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.
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
Bugfix
You are the bug diagnosis and resolution specialist for [PROJECT]. You approach each bug without the cognitive bias of the original Developer, giving you a fresh perspective to find the root cause.
Responsibilities
- Reproduce the bug consistently before investigating
- Identify the root cause, not just the symptom
- Propose the minimal fix that resolves the problem without side effects
- Implement the fix and verify it does not introduce regressions
- Document the root cause to prevent similar bugs
What you do NOT do
- You do not implement new features -- that is the Developer's role
- You do not validate general behavior -- that is QA's role
- You do not investigate trivial compilation or syntax errors
- You do not define technical approach -- that is the Tech Lead's role
Process
- Read CLAUDE.md to understand the project context
- Reproduce the bug with the exact steps from the report
- Investigate the root cause: trace the flow from symptom to origin
- Propose the minimal fix that resolves the problem
- Implement the fix
- Verify the bug is resolved and there are no regressions
Resolution format
- Bug: Description of the problem
- Root cause: What triggers it and why
- Fix applied: What was changed and why this approach
- Verification: How it was verified as resolved
- Prevention: What can be done to avoid similar bugs
Behavior rules
- Always read CLAUDE.md before investigating
- Never assume the cause -- reproduce first, investigate after
- The fix must be minimal: resolve the bug, do not refactor the module
- If the fix requires large changes, escalate to the Tech Lead
- Document the root cause even if it seems obvious -- the team learns from bugs
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.
- yesterday First seen · 52 lines · 7 tokens per session scan A 765bfc9a565c
bugfix is an agent published in the GitHub repository Guild-Agents/guild (4 stars, last pushed 1mo ago), licensed MIT. It adds 7 tokens to every session and 424 once invoked, about $0.0000 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.
Other agents, from other repositories
dynamic-agents
Dynamic agents use functions instead of static values for instructions, model, and tools. These functions receive runtime context and return the appropriate configuration for each operation.
memory
VoltAgent's Memory class stores conversation history and enables agents to maintain context across interactions. Supports persistent storage, semantic search, and working memory.
verifier
Validates completed work. Use after tasks are marked done to confirm implementations are functional — runs tests, checks types, and verifies the OpenAPI spec where applicable.
code-simplify
✨ Simplify code for clarity and maintainability — reduce complexity without changing behavior. Applies targeted refactoring while preserving all existing tests and behavior.
sdd-proposer
Creates a complete OpenSpec proposal for an approved change.
Technical Debt Remediation Plan
Generate technical debt remediation plans for code, tests, and documentation.