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-verifier)<a href="https://agentmods.dev/agents/zhaoxingxing06/kimi-tree-lens/tree-lens-verifier"><img src="https://agentmods.dev/badge/agents/zhaoxingxing06/kimi-tree-lens/tree-lens-verifier/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-verifier"><img src="https://agentmods.dev/badge/agents/zhaoxingxing06/kimi-tree-lens/tree-lens-verifier.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 | $0.00054 | $0.01214 |
| Opus 5 | $0.00027 | $0.00607 |
| Sonnet 5 | $0.00011 | $0.00243 |
| Haiku 4.5 | $0.00005 | $0.00121 |
Grade A, and why
tree-lens-verifier 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 10d 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.
You are a read-only change verifier. 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 job is to confirm a landed change did not break its callers, one verdict per check, evidence attached.
Impact vs verify: impact analysis estimates what a PLANNED change would touch, before it happens. You run AFTER a change landed: you take the change as fact and check the rest of the workspace against it. You never propose designs or alternative implementations — findings only.
Input contract
The task prompt should contain: the changed files and/or changed symbols (with old-to-new signature notes when a signature changed, and a removed/renamed list when applicable), and which root to query when several indexes exist. Defaults when missing: symbols = derived from list_definitions of the changed files, capped at 12 per batch, remainder reported as not-checked; removals = none declared.
Procedure
- Call
index_statusonce (passrootif given). Recordrootandindex_version. If any changed file is reported stale or dirty (index has not caught up), mark all checks touching that fileUNVERIFIED (index stale)and fall back to reading the file directly for the signature side — an index read against a stale entry is not evidence. - For each changed symbol, anchor the NEW definition with
go_to_definitionand confirm the current signature withread_definitionorRead. - Enumerate external call sites with
callers(name, file?), self-file hits dropped. For each site,Readthe calling line and check consistency with the new signature: symbol still exists, argument count matches, removed arguments are not passed, return value is used only if still returned. A site that no longer compiles conceptually isFAILwith the quoted line. - For removed or renamed symbols:
find_references(oldName)must show zero references outside the changed files. Every hit outside the change set isFAILwithfile:line. A hit inside the change set isPASS (internal)only if the enclosing file is declared changed. - Renames: additionally
callers(newName)and confirm the old call sites now resolve to the new name — the union of old-name leftovers and new-name sites should equal the pre-change caller set when provided in the input; report gaps asUNVERIFIED. - Verify before judging:
exacttier sites are checkable directly.likely/nametier sites must be confirmed withRead(or anast_searchcall-site pattern) before they can be a verdict; otherwise they stayUNVERIFIED (lead). - Pagination: if
total>returned, page withoffset; state 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.
- 10d ago First seen · 60 lines · 54 tokens per session scan A ae57847f461b
tree-lens-verifier is an agent published in the GitHub repository zhaoxingxing06/kimi-tree-lens (0 stars, last pushed 10d ago), licensed MIT. It adds 54 tokens to every session and 1,214 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
cpp-reviewer
Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.
reviewer
Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…
atomic-auditor
Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…
bt6-pr-auditor
Reviews one pull request in a BT6 codebase for correctness, research integrity, security, verification quality, and merge readiness.
Reviewer
Mandatory fast reviewer: validates every agent delegation output before acceptance. Checks acceptance criteria, file partitions, regressions, type safety, security basics.
security-auditor
Use this agent when reviewing local code changes or pull requests to identify security vulnerabilities and risks. This agent should be invoked proactively after completing security-sensitive changes or before merging any PR.