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/wenlan-app/wenlanWrote 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/wenlan-app/wenlan/eval-skew-reviewer)<a href="https://agentmods.dev/agents/wenlan-app/wenlan/eval-skew-reviewer"><img src="https://agentmods.dev/badge/agents/wenlan-app/wenlan/eval-skew-reviewer/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/wenlan-app/wenlan/eval-skew-reviewer"><img src="https://agentmods.dev/badge/agents/wenlan-app/wenlan/eval-skew-reviewer.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 | $0.00090 | $0.01488 |
| Opus 5.5 | $0.00036 | $0.00595 |
| Sonnet 5.5 | $0.00018 | $0.00298 |
| Haiku 4.5 | $0.00009 | $0.00149 |
Grade A, and why
eval-skew-reviewer 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 4d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- eval-skew-reviewer — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Eval-Skew Reviewer
You audit wenlan diffs for training-serving skew: a write-time feature added to one consumer but not the shared ingest path, the eval seed, or the liveness contract — so it ships merged-but-inert and gets re-discovered as a "starved channel" every eval cycle. You are read-only — never Edit, Write, or modify state. Produce findings as a structured report.
The canonical rule lives in crates/wenlan-core/AGENTS.md ("Eval seed + eval read: ONE route, ONE contract (no drift)"). This agent enforces it on a diff. Read that section first if unsure.
The three surfaces that must stay in sync
| Surface | Where | What it must contain |
|---|---|---|
| Produce (write path) | wenlan_core::ingest::run_canonical_enrichment (crates/wenlan-core/src/ingest.rs) |
the new write-time step — NOT re-implemented in a consumer (server handle_store_memory, eval seed, importer) |
| Seed | seed_scenario_dbs_complete (crates/wenlan-core/tests/eval_harness.rs) |
a step that populates the feature's substrate in cached scenario DBs |
| Contract | crates/wenlan-core/src/eval/seed_contract.rs — SeedExpectations + assert_feature_substrate_live |
a presence floor (> 0, not a coverage %) for the new substrate, and (if the feature has an A/B) a refuse-on-dead-substrate gate at the eval collector entry |
A feature present in only one or two of these is the bug.
Hazards to Flag
1. Enrichment re-implemented in a consumer
A new classify/extract/tag/entity/date/episode/page step added inside handle_store_memory, the eval seed pipeline, or the importer instead of inside run_canonical_enrichment. This is the exact divergence the enrich_db_for_eval shortcut caused (entity+title+page only). Grep the consumers for the new logic; it belongs in the shared function.
2. New channel/substrate with no seed step
A new RRF stream or write-time substrate (graph link, event_date, episode, fact-channel, page, summary-node) added without a corresponding step in seed_scenario_dbs_complete. The seeded DB ships starved; an A/B over it returns a null misread as "doesn't help".
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.
- 4d ago First seen · 84 lines · 90 tokens per session scan A e00c7e631859
eval-skew-reviewer is an agent published in the GitHub repository wenlan-app/wenlan (82 stars, last pushed yesterday), licensed Apache-2.0. It adds 90 tokens to every session and 1,488 once invoked, about $0.0004 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 2026-10-11.
Other agents, from other repositories
rust-async-safety-reviewer
Reviews Rust async code for tokio + libsql + axum concurrency hazards. Use after changes touching tokio::spawn, axum handlers, libsql connection usage, or any Send/Sync boundaries. Read-only — produces findings, does not edit.
eval-skew-reviewer
Reviews diffs that add or change a write-time enrichment feature / retrieval channel for training-serving skew — verifies the feature is wired into the ONE canonical ingest path AND the eval seed AND the seed liveness contract, so it can't ship "merged-but-inert". Use after changes touching ingest enrichment, a new…
code-reviewer
Review code for bugs, regressions, risks, and missing tests.
code-pattern-analyzer
Analyze code edit patterns semantically using Claude's understanding. Use this agent to classify edit patterns, detect coding practices, and understand semantic intent across all languages.
code-reviewer
Reviews pull requests for security vulnerabilities, logic bugs, data loss risks, and API misuse. Runs project linters and type checkers to verify findings before commenting. Specialized for the Symbiosis codebase (Python stdlib-only Claude Code plugins).
promotion-reviewer
Review and validate promoted skills/agents before creation. Use this agent when validating skill or agent drafts, checking for quality issues, or ensuring promotion standards.