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 d-padmanabhan/agent-engineering-handbook --skill multi-perspective-reviewgit clone --depth 1 https://github.com/d-padmanabhan/agent-engineering-handbookWrote 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/d-padmanabhan/agent-engineering-handbook/multi-perspective-review)<a href="https://agentmods.dev/skills/d-padmanabhan/agent-engineering-handbook/multi-perspective-review"><img src="https://agentmods.dev/badge/skills/d-padmanabhan/agent-engineering-handbook/multi-perspective-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.
<a href="https://agentmods.dev/skills/d-padmanabhan/agent-engineering-handbook/multi-perspective-review"><img src="https://agentmods.dev/badge/skills/d-padmanabhan/agent-engineering-handbook/multi-perspective-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Agent Snooping · line 31 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
- medium Agent Snooping · line 33 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00153 | $0.03067 |
| Opus 5 | $0.00077 | $0.01533 |
| Sonnet 5 | $0.00031 | $0.00613 |
| Haiku 4.5 | $0.00015 | $0.00307 |
Grade A, and why
multi-perspective-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 9d 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 — 255 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Multi-Perspective Review
A structured panel review framework for any architecture, vendor, strategy, or design decision. Embeds 5-7 expert perspectives, attaches industry-precedent evidence to every assertion, and uses a weighted scoring model so the user can influence outcomes by adjusting how much emphasis each advisor receives.
Companion rules:
100-core.mdc- core engineering principles015-context-engineering.mdc- prompt packing, retrieval, compaction
When to invoke
Use when the user asks for:
- "Panel review" / "stakeholder perspectives" / "advisory panel"
- "Pro/con analysis across multiple lenses"
- "Weighted recommendation" / "strategic review"
- "What would my CTO / Security / Finance say about this?"
- Re-weighting an existing review with a different emphasis
- A structured architecture / vendor / strategy decision that has multiple valid framings
Do not use for:
- Single-lens reviews (just call the right specialist skill)
- Creating or technically reviewing a production architecture; use the system design skill (
${HANDBOOK_ROOT}/skills/system-design/SKILL.md), then use this skill only when stakeholder weighting is needed - Decisions where one perspective dominates by mandate (compliance verdict, security veto)
- Independent assurance or required human approval; one model simulating multiple advisors is not independent verification. Use the independent verification skill (
${HANDBOOK_ROOT}/skills/independent-verification/SKILL.md) - Quick judgement calls that do not need a structured trade-off
The Six Golden Rules
- Every advisor has a coherent lens. Not "what should we do" but "what is this decision as seen through this lens".
- Every assertion carries an industry-precedent pair. What worked elsewhere; what blew up elsewhere.
- Weights always sum to 100%. Force the user to make trade-offs explicit.
- Votes are bounded (typically -2..+2). No infinite scales; no abstentions.
- Contested decisions (within ~0.15 of a band boundary) are flagged - the outcome is sensitive to re-weighting.
- Never silently use the default profile. Always prompt; defaulting to balanced hides bias.
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.
- 9d ago First seen · 255 lines · 153 tokens per session scan A cd469371219d
multi-perspective-review is a skill published in the GitHub repository d-padmanabhan/agent-engineering-handbook (17 stars, last pushed today), licensed MIT. It adds 153 tokens to every session and 3,067 once invoked, about $0.0008 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 2026-09-03.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…