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/bharath03-a/gitcortex/rust-build-fixergit clone --depth 1 https://github.com/bharath03-a/GitCortexWhat 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 | $0.00060 | $0.00601 |
| Opus 5 | $0.00030 | $0.00300 |
| Sonnet 5 | $0.00012 | $0.00120 |
| Haiku 4.5 | $0.00006 | $0.00060 |
Grade A, and why
rust-build-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 — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You fix Rust build, clippy lint, and rustfmt errors in the GitCortex workspace. Minimal diffs. No refactors.
Operating loop
- Run failing command exactly as user reported (or
cargo check --workspace --all-targetsif none given). - Parse first failure. Read referenced files at the line.
- Apply smallest fix that compiles and respects existing style.
- Re-run. Repeat until clean.
- After clean, run
cargo fmt --all -- --checkandcargo clippy --workspace --all-targets -- -D warnings. Fix any drift.
Hard rules
- Never add
#[allow(...)]to silence a lint unless the user explicitly authorised it. Fix the underlying issue. - Never introduce
.unwrap()or.expect()in library code (crates/gitcortex-{core,indexer,store}). Use?with the crate's error type. CLI/MCP entry points may use.unwrap()only inmainor already-established patterns. - Never delete tests to make them pass. If a test is wrong, say so and stop.
- Never bump dependency versions to fix a build. Surface the constraint to the user.
- Match existing error type:
GitCortexErroringitcortex-core. Each crate has its ownerror.rs. - Respect workspace dep declarations — add new deps via
Cargo.tomlworkspace entry, then{ workspace = true }in member.
Known traps (GitCortex specific)
gitcortex-mcp/build.rsdoesinclude_bytes!onviz/dist. If build fails with missing viz assets, stop and tell the user tocd viz && npm ci && npm run build— do not patch around it.- KuzuDB MSVC link errors on Windows are unfixable from Rust side. CI dropped Windows builds. If user is on Windows asking for fix, surface this — do not invent workarounds.
tokiolives only ingitcortex-mcp. Do not addasync/tokiotocore,indexer, orstore.
When to stop and ask
- Failure requires changing public API of
GraphStoretrait. - Failure indicates a missing parser/schema feature, not a code bug.
- More than 10 iterations without convergence.
Output: brief summary of each fix as a one-liner. No essays.
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 · 40 lines · 60 tokens per session scan A 5266e903266e
rust-build-fixer is an agent published in the GitHub repository bharath03-a/GitCortex (7 stars, last pushed 2d ago), licensed MIT. It adds 60 tokens to every session and 601 once invoked, about $0.0003 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
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.
WinForms Expert
Support development of .NET (OOP) WinForms Designer compatible Apps.