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.
npx skills add aaronartistzhang-afk/DailyWork --skill group-discussion-reviewergit clone --depth 1 https://github.com/aaronartistzhang-afk/DailyWorkWrote 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/skills/aaronartistzhang-afk/dailywork/group-discussion-reviewer)<a href="https://agentmods.dev/skills/aaronartistzhang-afk/dailywork/group-discussion-reviewer"><img src="https://agentmods.dev/badge/skills/aaronartistzhang-afk/dailywork/group-discussion-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/skills/aaronartistzhang-afk/dailywork/group-discussion-reviewer"><img src="https://agentmods.dev/badge/skills/aaronartistzhang-afk/dailywork/group-discussion-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 | $0.00199 | $0.01199 |
| Opus 5 | $0.00100 | $0.00600 |
| Sonnet 5 | $0.00040 | $0.00240 |
| Haiku 4.5 | $0.00020 | $0.00120 |
Grade A, and why
group-discussion-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 12d 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 — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Group Discussion Reviewer (engine)
Simulate a sharp product group-discussion review of a PRD. This is the high-fidelity, runnable engine: an 8-phase pipeline (Fact Ledger → Scenario Signals → Reviewer Roles → independent reviewers → Judge → P0 Gatekeeper + calibration → Final Composer) that ends in a two-axis verdict and a prioritized question list.
Scope: this engine reviews already-extracted PRD text / markdown. It does not fetch Lark/Feishu (or any) URLs and does not expand embedded sheets. Export or paste the PRD body first, then feed it in.
When to use
- The user wants a PRD stress-tested the way a real product group review would.
- They ask whether a PRD can pass, what the P0 blockers are, or whether it's concrete enough to even enter group discussion (组内准入).
- They want disciplined severity (P0 reserved for true approval blockers; everything else P1/P2), not a generic checklist.
If there is no API key available, or the user just wants the review framework applied
in-conversation, use the sibling skill group-discussion-reviewer-methodology instead.
Setup (one-time)
Requires Node ≥ 20 (no npm dependencies) and an OpenAI-compatible API key.
cd skills/group-discussion-reviewer
cp .env.example .env # then fill in OPENAI_API_KEY
npm test # optional: 183 offline tests should pass
Environment:
| Var | Default | Notes |
|---|---|---|
OPENAI_API_KEY |
— (required) | The API key. |
OPENAI_BASE_URL |
https://api.openai.com/v1 |
Set to your own OpenAI-compatible gateway. |
OPENAI_MODEL |
gpt-4.1-mini |
Any chat/completions model id. |
OPENAI_AUTH_STYLE |
bearer if no base url, else query |
bearer = Authorization header; query = key as ?ak= (for gateways that take the key in the URL). |
How to run
# review a PRD file (challenge mode, Chinese, full depth)
node bin/review-prd.mjs --file path/to/prd.md
# pipe from stdin; only the P0 section, in English
cat prd.md | node bin/review-prd.mjs --mode standard --depth p0 --lang en
# full JSON (review + usage + cost). add --artifacts to include internal pipeline detail
node bin/review-prd.mjs --file prd.md --json
What ships with it
39 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- .env.example 724 B
- bin/review-prd.mjs 5.5 KB runs code
- LICENSE 1.0 KB
- package.json 431 B
- README.md 3.7 KB
- src/feedbackPrompt.mjs 1.8 KB runs code
- src/finalReviewComposer.mjs 14 KB runs code
- src/llmGatewayClient.mjs 3.7 KB runs code
- src/multiReviewerPipeline.mjs 8.8 KB runs code
- src/openaiReview.mjs 6.9 KB runs code
- src/p0Gatekeeper.mjs 27 KB runs code
- src/prdChunking.mjs 2.4 KB runs code
- src/prdFactLedger.mjs 11 KB runs code
- src/productReviewCalibration.mjs 25 KB runs code
- src/reviewCost.mjs 2.9 KB runs code
- src/reviewerPrompt.mjs 13 KB runs code
- src/reviewerRoles.mjs 5.9 KB runs code
- src/reviewJudge.mjs 11 KB runs code
- src/reviewPipelineMode.mjs 425 B runs code
- src/reviewRubric.mjs 3.4 KB runs code
- src/scenarioSignals.mjs 2.6 KB runs code
- test/cli.smoke.test.mjs 6.5 KB runs code
- test/finalReviewComposer.test.mjs 7.5 KB runs code
- test/fixtures/p0GatekeeperReviewLevelGoldSet.json 22 KB
- test/fixtures/productReviewCalibrationGoldSet.json 9.9 KB
- test/llmGatewayClient.test.mjs 4.7 KB runs code
- test/multiReviewerPipeline.test.mjs 32 KB runs code
- test/openaiReview.test.mjs 18 KB runs code
- test/p0Gatekeeper.test.mjs 37 KB runs code
- test/prdChunking.test.mjs 2.6 KB runs code
- test/prdFactLedger.test.mjs 5.1 KB runs code
- test/productReviewCalibration.test.mjs 18 KB runs code
- test/reviewCost.test.mjs 2.6 KB runs code
- test/reviewerPrompt.test.mjs 6.5 KB runs code
- test/reviewerRoles.test.mjs 3.6 KB runs code
- test/reviewJudge.test.mjs 14 KB runs code
- test/reviewPipelineMode.test.mjs 1.2 KB runs code
- test/reviewRubric.test.mjs 2.2 KB runs code
- test/scenarioSignals.test.mjs 2.1 KB runs code
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.
- 12d ago First seen · 86 lines · 0 tokens per session scan A 565bc95fd361
group-discussion-reviewer is a skill published in the GitHub repository aaronartistzhang-afk/DailyWork (1 stars, last pushed 14d ago), licensed MIT. It adds 199 tokens to every session and 1,199 once invoked, about $0.0010 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 skills, from other repositories
optimizing-clickhouse-and-hogql-queries
Workflow for optimizing ClickHouse and HogQL queries. Use when a HogQL query, query runner, insight, or report is too slow; when a hand-written ClickHouse query (via syncexecute or in a migration) is too slow; when ClickHouse times out or hits memory limits; when investigating a slow system.querylog row; or when…
dynamic-workflows
Designs and runs task-specific JavaScript harnesses with the workflow tool. Use for broad, long-running, highly structured, or adversarial work that benefits from many isolated agents: exhaustive audits, root-cause investigations, research, large triage queues, competing proposals, repeated verification, and…
adding-product-alerting
Recommended repo-engineering guide when adding alerting to a PostHog product or extending the shared alerts platform. Routes lifecycle state machines, AlertPolicy, destinations, HogFunction dispatch, email, fixed-cadence and calendar scheduling, insight evaluation, the AlertWizard, and shared alert editor components.…
adding-mcp-store-servers
Add a third-party MCP server (Linear, Notion, GitHub, ...) to the PostHog MCP store catalog. Use when asked to "add X to the MCP store", expand the MCP server marketplace, or fix a broken catalog entry. Covers finding the vendor's remote MCP endpoint, probing it (handshake, OAuth discovery, DCR), authoring the catalog…
subagent-orchestration
How and when to delegate work to subagents via the subagent tool (Explore, Plan, General). Use when a task involves codebase recon, implementation planning, or actual code changes that would benefit from an isolated context window instead of doing it all inline.
managing-reminders
Create and manage PostHog reminders — private, human-paced nudges that fire as in-app notifications on a schedule, optionally linked to a PostHog resource. Use when the user says "remind me to…", wants a one-off or recurring nudge (daily/weekly/monthly/yearly, a cron schedule, or a specific date/time), wants to be…