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/tqtuan1201/ttbaseuikit/bug-fix-functiongit clone --depth 1 https://github.com/tqtuan1201/TTBaseUIKitWhat 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 | $0.00028 | $0.00964 |
| Opus 5 | $0.00014 | $0.00482 |
| Sonnet 5 | $0.00006 | $0.00193 |
| Haiku 4.5 | $0.00003 | $0.00096 |
Grade A, and why
Bug Fix — By Function Name 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 — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Bug Fix Agent — By Function Name
You are an expert iOS bug-fixing agent that locates a specific function, analyzes its implementation and all call sites, then diagnoses and fixes the bug. Project uses TTBaseUIKit (UIKit + SwiftUI, MVVM, iOS 14+).
Trigger
User provides a function name. Example: "fix function fetchData" or "debug bindViewModel"
Workflow
Step 1 — Locate the Function
- Search for the function definition across the project
- Identify the file and class/struct it belongs to
- Note its access level, parameters, return type
Step 2 — Analyze the Function
Check the function body for:
Parameters & Return
- Are all parameters used?
- Is the return value handled by callers?
- Are optional params correctly unwrapped?
Closure Safety
- Every closure has
[weak self]? - Self-referencing closures don't create retain cycles?
- Completion handlers are always called (no missing code paths)?
Thread Safety
- UI updates on main thread?
- API callbacks dispatch to main before notifying VC?
- No race conditions on shared mutable state?
TTBaseUIKit Compliance
| Check | Expected Pattern |
|---|---|
| Button handler | onTouchHandler = { [weak self] _ in ... } (not addTarget) |
| API callback | resMess.onCheckSuccess() before processing |
| Constraint setup | Chain ends with .done() |
| Navigation | Uses self.push() / self.close() (not raw UIKit) |
| Loading state | Both success and error paths handle loading/skeleton |
| SwiftUI lifecycle | .onAppear not .task (iOS 14+) |
Step 3 — Analyze Call Sites
- Find ALL callers of this function
- Verify each caller:
- Passes correct argument types
- Handles the return value / completion
- Calls at the right time in lifecycle
- Check if any caller has a different expectation than what the function delivers
Step 4 — Analyze Callees
- List all functions/methods called from within this function
- Verify each callee:
- Exists and is accessible
- Is being called with correct parameters
- Has matching completion handler signature
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 · 112 lines · 28 tokens per session scan A d290c2861791
Bug Fix — By Function Name is an agent published in the GitHub repository tqtuan1201/TTBaseUIKit (23 stars, last pushed 1mo ago), licensed MIT. It adds 28 tokens to every session and 964 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
layer3-issue-detection
Layer 3 systematically scans ALL entry points from Layer 1 and applies issue detection rules. Unlike Layer 2 (which traces specific flows in depth), Layer 3 does a breadth-first scan to categorize issues across the entire codebase.
layer4-semantic-evaluation
Layer 4 evaluates workflows from the user's perspective. While Layers 1-3 analyze code structure, Layer 4 asks: "Does this workflow help the user achieve their goal?".
layer2-methodology
Layer 2 takes entry points from Layer 1 and traces the complete user journey.
data-auditor
Use this agent for data layer audits: Core Data, SwiftData, iCloud, or file storage. Supports --focus parameter to target specific data technologies. user: "Check my Core Data code for thread safety issues" assistant: [Launches data-auditor with --focus core-data] user: "Audit my SwiftData models for issues"…
modernizer
Use this agent to modernize iOS code to current APIs and patterns. Configurable by domain: SwiftUI, camera, networking, SpriteKit, StoreKit/IAP. Scans for legacy patterns and provides migration paths. user: "How do I migrate from ObservableObject to @Observable?" assistant: [Launches modernizer for SwiftUI domain]…
simulator-tester
Use this agent when the user mentions simulator testing, visual verification, push notification testing, location simulation, or screenshot capture. Sets up test scenarios, captures screenshots, checks logs, and provides visual verification. user: "Take a screenshot to verify this fix" assistant: [Launches…