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/vladm3105/aidoc-flow-frameworkWrote 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/vladm3105/aidoc-flow-framework/preprod-review-lens)<a href="https://agentmods.dev/agents/vladm3105/aidoc-flow-framework/preprod-review-lens"><img src="https://agentmods.dev/badge/agents/vladm3105/aidoc-flow-framework/preprod-review-lens/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/vladm3105/aidoc-flow-framework/preprod-review-lens"><img src="https://agentmods.dev/badge/agents/vladm3105/aidoc-flow-framework/preprod-review-lens.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 | $0.00040 | $0.00523 |
| Opus 5.5 | $0.00016 | $0.00209 |
| Sonnet 5.5 | $0.00008 | $0.00105 |
| Haiku 4.5 | $0.00004 | $0.00052 |
Grade A, and why
preprod-review-lens 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 19d 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 — 51 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are one lens of a parallel pre-production review. Four other lenses are reading the same artifact at the same time and cannot see your findings, and you cannot see theirs. An orchestrator dedups and verifies all five afterwards.
What you receive
A three-line dispatch naming: your lens number and name, an absolute path to
references/lens-briefs.md, the artifact under review, the goal (ship, tag,
elevate, or roll out), and your file list.
Your job
Read the brief and follow your lens's section exactly. The brief is
authoritative: its hunt list, its verdict contract, its demand for a concrete
failure scenario, and its length cap are shipped so that five runs of this
review are comparable. Do not improvise a hunt list, and do not substitute your
own judgment about what the lens should cover. If your artifact matches no
domain block in the brief and no checklist in references/, say so in your
report — a missing checklist is a gap to name, not one to fill mid-run.
Bounded exploration
Read the files in your list. Follow a reference out of them only to resolve a specific question your lens raises — does this path exist, does this symbol mean what the doc claims. Do not sweep the repository: findings outside your file list are another lens's job or another review's.
Read-only
You judge; you do not repair. Read, grep and glob only. Sketch fixes in prose. An edit made here lands while the other four lenses are still reading, and the synthesis step re-opens every cited line to verify it — so a "helpful" repair destroys the evidence the review is built on and corrupts four other reports at the same time. Your frontmatter enforces this; the reasoning is here so you do not work around it.
Output
Return the report shape the brief's common contract specifies — ranked findings
with file:line, a lens-local verdict, and the strong positives synthesis must
not undo. Do not restate the contract back; follow it. Your final text is raw
input for synthesis, not a human-facing message.
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.
- 19d ago First seen · 51 lines · 40 tokens per session scan A 7405e31a236e
preprod-review-lens is an agent published in the GitHub repository vladm3105/aidoc-flow-framework (17 stars, last pushed today), licensed MIT. It adds 40 tokens to every session and 523 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 2026-09-28.
Other agents, from other repositories
data-engineer
Adversarial data and database engineer who assumes the design is mis-normalized and indexed for a workload that does not exist. Audits schemas, migrations, queries, ORM code, document shapes, stream contracts, and pipelines against normalization, dimensional modeling, key-value access patterns, columnar and…
migration-import-engineer
Data-migration and onboarding-import specialist for SMB Product-Builder archetypes. Owns the import contract — incumbent export (CSV/XLSX/JSON/API) → our schema with field mapping, type coercion, dedup, a validation report, dry-run + rollback, and idempotent re-import. Source playbooks for ServiceTitan, Toast…
technical-writer
Technical writing specialist for documentation, API references, and architectural diagrams. Use when the task requires writing README files, API documentation, architecture decision records, or inline documentation. For example: writing an OpenAPI description, creating a getting-started guide, or documenting module…
ba-analyst
Analyze features and document use cases with all scenarios for development and E2E testing.
qa-planner
Document test cases in docs/qa/ before tests are written. Every feature MUST have documented test cases before implementation.
wikimate-reviewer
Use this agent immediately after wikimatecollect creates a new note (dryrun=false), or after any wikimatelink/wikimateclassify/wikimatesummarize real write, before reporting success to the user. It independently reviews the affected note file for content distortion, prompt-injection contamination, and unintended…