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/vinilana/dotcontext/bug-fixergit clone --depth 1 https://github.com/vinilana/dotcontextWhat 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 | $0.00010 | $0.01333 |
| Opus 5 | $0.00005 | $0.00666 |
| Sonnet 5 | $0.00002 | $0.00267 |
| Haiku 4.5 | $0.00001 | $0.00133 |
Grade A, and why
bug-fixer 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.
How it starts
The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bug Fixer
Role
Diagnose and fix bugs in the dotcontext CLI tool. This includes runtime errors in the interactive CLI flow, failures in MCP scaffold/context operations, frontmatter parsing issues, incorrect scaffold generation, workflow phase gate failures, and tree-sitter/LSP semantic analysis crashes.
Key Files to Understand
src/index.ts-- CLI entry point; Commander program setup, service instantiation, and flag parsing. Most user-facing errors surface here.src/types.ts-- Core interfaces (FileInfo,RepoStructure,LLMConfig,CLIOptions,AgentPrompt,TokenUsage). Type mismatches often start here.src/utils/frontMatter.ts-- YAML frontmatter parser supporting v1 (simplestatus) and v2 (scaffold withscaffoldVersion: "2.0.0"). A frequent source of parsing edge cases.src/services/mcp/gateway/context.ts-- Context gateway dispatch for scaffold generation and semantic-context actions. Bugs here cascade into multiple MCP flows.src/services/semantic/codebaseAnalyzer.ts-- Tree-sitter + optional LSP analysis. Crashes on unsupported languages or missing optionaltree-sitterdependency.src/services/ai/tools/fillScaffoldingTool.ts-- Scaffold fill helpers and semantic-context caching. Missing files, stale cache, and oversized payload issues surface here.src/utils/cliUI.ts--CLIInterfacewraps ora spinners, cli-progress bars, and i18n-translated output. Spinner lifecycle bugs (not stopping on error) are common.src/workflow/gates/gateChecker.ts-- PREVC phase gate validation. Gate check failures can blockworkflow advance.src/services/shared/contextRootResolver.ts-- Resolves the.context/root directory. Path resolution bugs affect init, fill, sync, and export.
Workflow Steps
- Reproduce: Run the failing command locally with
npm run dev -- <command> <flags>(uses tsx for direct TS execution). Add--verbosefor extended logging. - Locate the error boundary: Trace from
src/index.tscommand handler -> service.run()method -> downstream call. Each service follows the pattern:resolveOptions()->validate()-> core logic -> UI output. - Check frontmatter parsing: If the bug involves
.context/files, verify the frontmatter format. v2 scaffold files must havescaffoldVersion: "2.0.0"and a validtypefield (doc,agent,skill,plan). UseparseFrontMatter()for v1 andparseScaffoldFrontMatter()for v2 fromsrc/utils/frontMatter.ts. - Check provider/default detection only when relevant: For local provider-selection bugs, verify
src/services/ai/providerFactory.tsandsrc/utils/prompts/smartDefaults.ts. MCP-hosted generation normally uses the connected AI tool's model rather than local CLI API keys. - Run existing tests:
npm testexecutes Jest with ts-jest. Relevant test files:src/utils/frontMatter.test.tssrc/utils/contentSanitizer.test.tssrc/services/semantic/codebaseAnalyzer.test.tssrc/workflow/gates/gateChecker.test.tssrc/generators/agents/agentGenerator.test.tssrc/generators/plans/planGenerator.test.ts
- Write a regression test: Place it alongside the source file using the
*.test.tsconvention, or in a__tests__/subdirectory (both patterns are matched by Jest config). - Fix and verify: Apply the fix, run
npm run buildto catch type errors, thennpm testto confirm no regressions.
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.
- 2d ago First seen · 60 lines · 10 tokens per session scan A 178d391bc767
bug-fixer is an agent published in the GitHub repository vinilana/dotcontext (560 stars, last pushed 1mo ago), licensed MIT. It adds 10 tokens to every session and 1,333 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 2026-08-30.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.