What is panel-review?

A one-pass adversarial review of a written implementation plan before coding begins, intended for changes involving at least three modules or an unclear scope.

Use it to review a plan file before a multi-module or ambiguous code change.

It provides a challenge to the plan before implementation, when correcting omissions is less costly.

How senda-labs/DQIII8 configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to senda-labs/DQIII8. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/senda-labs/DQIII8/main/.claude/skills/panel-review/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/senda-labs/DQIII8

Made for: Claude Code.

Or install dqiii8, the plugin that ships this one along with the rest of its 22 skills, 14 commands, 17 agents.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/senda-labs/dqiii8/panel-review/github.svg)](https://agentmods.dev/skills/senda-labs/dqiii8/panel-review)

Your own site

<a href="https://agentmods.dev/skills/senda-labs/dqiii8/panel-review"><img src="https://agentmods.dev/badge/skills/senda-labs/dqiii8/panel-review/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/senda-labs/dqiii8/panel-review"><img src="https://agentmods.dev/badge/skills/senda-labs/dqiii8/panel-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 31 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,068 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00031	$0.02068
Opus 5	$0.00015	$0.01034
Sonnet 5	$0.00006	$0.00414
Haiku 4.5	$0.00003	$0.00207

Measured 12d ago against content hash c6bf38adc4e5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

panel-review 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.

.claude/skills/panel-review/SKILL.md · 151 lines

How it starts

The opening of the file, as written. The whole thing — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/panel-review — Plan Adversarial Review

Run before implementing any plan that touches ≥3 modules or has ambiguous scope, after plan-mode design and before writing code.

Usage

/panel-review <plan-file>

Runs python3 bin/tools/panel_review.py <plan-file>.

What it does

Under the Anthropic-only directive (no non-Anthropic provider API is operative today), there is no multi-seat NIM pre-filter alongside the Opus pass — it would route through dead infrastructure. If the multi-tier chain is ever reactivated (.claude/rules_db/archive/multi-tier-dormant-2026-08.md), re-adding a pre-filter is a deliberate future decision, not an automatic revert of this one.

Exactly ONE Opus adversarial pass (code-reviewer agent → claude-opus-5), the entire review. This spends the operator's own Claude Code session quota — no ANTHROPIC_API_KEY is configured, so it runs as a nested claude -p OAuth call. It reuses the existing single-Opus-escalation allowance defined in .claude/rules_db/dqiii8-plan-gate.md (max 1 per task) — it is not an additional or second Opus budget. No iteration, no forced dissent, no re-voting loop: one pass, one verdict. It reads the plan and the repo and must cite file:line for every finding — uncited findings are discarded by the orchestrator, not just flagged.
Report: written to database/audit_reports/panel-review-YYYY-MM-DD-HH-<slug>.md. Never committed. database/audit_reports/*.md is fully gitignored, no negation — a .gitignore negation here would put a report containing a real infra IP or credential literal one git add -A away from being staged. Durability for these reports comes from the off-VPS backup channels documented in CLAUDE.md (backup_audit_docs.sh + telegram_audit_backup.py), not from git. .gitleaks.toml still carries the audit-docs-bare-ipv4 / audit-docs-password-literal rules scoped to this corpus — now mostly a defense-in-depth backstop against a future re-negation, but still worth running (gitleaks detect) over any new report as a manual habit, since these files never pass through the pre-commit hook at all while gitignored.
Verdict is advisory, not a gate. The tool reports; the calling session (CC) is responsible for addressing each cited finding before implementation proceeds.

Read the full file on GitHub · 151 lines

Changes

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 · 151 lines · 31 tokens per session scan A c6bf38adc4e5

Subscribe to this mod's changes

panel-review is a skill published in the GitHub repository senda-labs/DQIII8 (11 stars, last pushed 24d ago), licensed MIT. It adds 31 tokens to every session and 2,068 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 2026-08-30.

Claude Code Planning ai-agent ai-automation ai-orchestration ai-routing claude

using-adaptive-harness

Auto-mode bootstrap for adaptive-harness. Intercepts tasks, routes to optimal harness, evaluates results. Use on every task when adaptive-harness auto-mode is active.

SeongwoongCho/adaptive-harness · 39 tokens

task-taxonomy

Reference for the 6-axis task taxonomy used by adaptive-harness routing. Use when user asks how tasks are classified.

SeongwoongCho/adaptive-harness · 28 tokens

harness-registry

Manage the adaptive-harness pool: list, inspect, promote, demote harnesses. Use when user asks about harness status or wants to manage the pool.

SeongwoongCho/adaptive-harness · 37 tokens

skill-review-response

Use when a reviewer, CI bot, or another AI leaves feedback to address.

nyldn/claude-octopus · 19 tokens

sys-configure

Configure Claude Octopus — redirects to /octo:setup interactive wizard.

nyldn/claude-octopus · 18 tokens

continuum-tools-mcp

Connect MCP servers (Stdio/SSE/StreamableHTTP) to a Continuum agent, configure tool filtering, set up tool-context capture/injection (e.g. sessionid), and read run artifacts (UI widgets, structured tool data). Invoke when the user asks "connect MCP", "filesystem tool", "remote API tool", "auto-capture sessionid"…

shyftlabs/continuum · 94 tokens

DQIII8: Skill for Claude Code