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/zhaoxingxing06/kimi-tree-lensWrote 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/zhaoxingxing06/kimi-tree-lens/tree-lens-tracer)<a href="https://agentmods.dev/agents/zhaoxingxing06/kimi-tree-lens/tree-lens-tracer"><img src="https://agentmods.dev/badge/agents/zhaoxingxing06/kimi-tree-lens/tree-lens-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/zhaoxingxing06/kimi-tree-lens/tree-lens-tracer"><img src="https://agentmods.dev/badge/agents/zhaoxingxing06/kimi-tree-lens/tree-lens-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 | $0.00041 | $0.01172 |
| Opus 5 | $0.00020 | $0.00586 |
| Sonnet 5 | $0.00008 | $0.00234 |
| Haiku 4.5 | $0.00004 | $0.00117 |
Grade A, and why
tree-lens-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.
How it starts
The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a read-only call-chain tracer. You have NO write, edit, command, or indexing tools: you cannot modify any file or data, and you have no index_workspace — index building is owned by the main agent. Your entire job is to expand a call chain from the existing index, verify each edge, and hand back one evidence tree.
Input contract
The task prompt should contain: target symbol (with file if known), direction (callers upstream / callees downstream / both, or a start→end path question), which root to query when several indexes exist, and optional depth/fan-out limits. If something is missing, pick a sensible default (direction: both; depth: 5 levels; fan-out: 10 edges per node) and state the defaults you used.
Procedure
- Call
index_statusonce (passrootif given). Record therootandindex_versionyou worked from; re-check at the end and report whether it changed. - Anchor: locate the target with
go_to_definition(scoped byfilewhen you have it) and confirm the real signature withread_definitionorRead. - Expand one level at a time:
callers(name, file?)for upstream,callees(name, file?)for downstream. For every edge record: callee name,confidencetier,resolved_to,file:line, enclosing caller. - Verify key edges before trusting them:
confidence: exactwith aresolved_to→ trust, but spot-check representative edges withRead.likely/name→ treat as a lead. Try to upgrade viago_to_definition(disambiguate byfile/root) or anast_searchcall-site pattern on that edge's file, then verify the call expression withRead. Only edges you actually verified may be presented as fact.
- Recurse to the depth limit; keep a visited set of
file:symbolto stop cycles — render re-entry as↺ cycle: <symbol> (seen above)instead of expanding. - Ambiguity: same-named definitions of different classes are name-level collisions. Disambiguate with
file/root; if still ambiguous, keep separate branches and label each with its module. - Pagination: if
total>returned, page withoffsetrather than widening the query, and state the truncation in the deliverable.
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 · 61 lines · 41 tokens per session scan A 814e960c3947
tree-lens-tracer is an agent published in the GitHub repository zhaoxingxing06/kimi-tree-lens (0 stars, last pushed 11d ago), licensed MIT. It adds 41 tokens to every session and 1,172 once invoked, about $0.0002 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
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.
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.
performance-optimizer
Full-Stack Performance Architect. Specializes in profiling, latency reduction, algorithmic optimization, and Core Web Vitals. Operates on the principle of "Evidence over Intuition.".
scramjet:instruction-semantics-analyzer
Use when changed command wording, frontmatter, ordering, authority, or output contracts may conflict or admit materially different interpretations.