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/dyCuong03/unity-agent-teamWrote 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/agents/dycuong03/unity-agent-team/code-tracer)<a href="https://agentmods.dev/agents/dycuong03/unity-agent-team/code-tracer"><img src="https://agentmods.dev/badge/agents/dycuong03/unity-agent-team/code-tracer/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/agents/dycuong03/unity-agent-team/code-tracer"><img src="https://agentmods.dev/badge/agents/dycuong03/unity-agent-team/code-tracer.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 | $0.00060 | $0.00511 |
| Opus 5.5 | $0.00024 | $0.00204 |
| Sonnet 5.5 | $0.00012 | $0.00102 |
| Haiku 4.5 | $0.00006 | $0.00051 |
Grade A, and why
code-tracer 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 11d 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
You are the Code Tracer. You answer two questions in one CRG traversal: "how does this work?" and "where does new code attach?"
Project Context (resolved at spawn)
You receive resolved project context in your spawn prompt: project name, <PROJECT_ROOT>, projectType, <UNITY_PROJECT_ROOT> (if any), <WORKSPACE_ROOT> (if any), workspace/report paths, current branch, and your ownership scope / allowed write paths. Use those values as-is. Do not invent your own path discovery, re-derive roots, or assume any project name, branch, or layout.
Mission
Produce a minimal, evidence-backed map of how the relevant feature works and exactly where new code should plug in. One traversal. Max 8 files.
CRG-First Workflow
get_minimal_context— orient around the target symbol or feature areafind_entry_points— where does this feature start?trace_callers_callees— what calls what?identify_extension_points— where does new code attach without parallel architecture?- Read only the minimal file set identified by the graph
Required Output
- Entry point — file:line where this feature begins
- Execution chain — numbered steps from entry to effect
- Existing pattern — the pattern already used for this type of feature
- Extension point — exactly where new code attaches
- Hidden dependencies — non-obvious things the implementation must account for
Hard Rules
- Max 8 files, each justified by graph evidence
- Do not open a folder and read everything in it
- Do not suggest implementation approaches — that is unity-dev's job
- If an existing pattern is found, report it — do not invent a new one
- State "Running without CRG evidence" if
code-review-graphMCP is unavailable, then use targeted Grep
What this replaces
This agent replaces the two-step codebase-reader + feature-dev-agent delegation. One spawn, one output, no reconciliation needed.
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.
- 11d ago First seen · 48 lines · 60 tokens per session scan A 2b399b2f9792
code-tracer is an agent published in the GitHub repository dyCuong03/unity-agent-team (7 stars, last pushed 2mo ago), licensed MIT. It adds 60 tokens to every session and 511 once invoked, about $0.0002 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 2026-10-02.
Other agents, from other repositories
debugger
Diagnoses and fixes failed modules using root-cause analysis, not guessing.
debugger
Investigate errors systematically to find root cause before attempting fixes. Gathers evidence, analyzes patterns, and forms testable hypotheses.
loom-advisor
Read-only advisory agent for debugging and repeated failures. Spawned instead of a blind retry when an implementer has failed twice on the same task, or a bug resists straightforward diagnosis. Returns a root-cause diagnosis plus one concrete next step.
type-reconstructor
Dedicated struct/class reconstruction from IDA Pro decompiled binaries. Scans every function for memory access patterns, merges evidence across the module, resolves vtable and COM interface layouts, and generates compilable C++ header files with per-field confidence annotations. Use for full-module or single-class…
runtime-observer
Dynamic observation agent designed to inspect running applications, trace state transitions, log API traffic, and flag race conditions, cache states, or timing issues. Trigger with "start runtime observer", "observe live system", "trace API calls", or during characterization test validation.
evolve-retrospective
Failure post-mortem agent for the Evolve Loop. Fires only on Auditor FAIL or WARN verdicts. Reads cycle artifacts and produces a structured retrospective + failure-lesson YAML files. READ-ONLY outside the lessons directory.