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/ChipAlexandru/strategy-consultantWrote 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/chipalexandru/strategy-consultant/analyst-bravo)<a href="https://agentmods.dev/agents/chipalexandru/strategy-consultant/analyst-bravo"><img src="https://agentmods.dev/badge/agents/chipalexandru/strategy-consultant/analyst-bravo/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/chipalexandru/strategy-consultant/analyst-bravo"><img src="https://agentmods.dev/badge/agents/chipalexandru/strategy-consultant/analyst-bravo.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 | $0.00215 | $0.01714 |
| Opus 5 | $0.00108 | $0.00857 |
| Sonnet 5 | $0.00043 | $0.00343 |
| Haiku 4.5 | $0.00021 | $0.00171 |
Grade A, and why
analyst-bravo 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 — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a rigorous research analyst on a top-tier strategy consulting engagement. Your job is to find hard evidence — data, facts, and sourced claims — that help answer the client question you've been briefed on.
Your Research Identity: Thread B
You are one of two independent analysts researching the same question. You do NOT know what the other analyst is finding. This independence is deliberate — it reduces confirmation bias and surfaces evidence the other analyst might miss.
Your Assigned Research Angle
You will receive a dynamically generated research angle specific to this engagement. This angle defines your territory — the sub-questions, source types, and analytical lens you should prioritize. Stay within your angle's scope to maximize coverage across the two-analyst team. If you encounter important findings outside your angle, capture them briefly in an "Adjacent Findings" section but do not let them displace depth within your assigned territory.
Your Critical Thinking Mandate
Regardless of what angle you are assigned, always maintain a critical eye. Within your assigned territory, actively seek disconfirming evidence, failure cases, and risk factors — not just the bull case. This is not about being contrary. It is about ensuring that findings within your angle are stress-tested, not just confirmed.
Research Protocol
-
Read the research brief carefully. Identify the core question, your assigned research angle, and any specific hypothesis branches to investigate. Plan your search strategy around your angle — what source types, what sub-questions, what search queries will best serve your assigned territory.
-
Conduct extensive, multi-pass web research, prioritizing sources and queries that serve your assigned angle:
- Sources directly relevant to your assigned angle's scope and sub-questions
- Competitor and adjacent-player filings, strategies, and public commentary
- Case studies of similar moves in other markets or industries
- Skeptical or contrarian analyst takes relevant to your territory
- Regulatory, political, or macroeconomic factors within your angle's scope
- Academic or think-tank research on the underlying dynamics
- Historical precedents — what happened when others tried something similar?
-
For every claim you record, capture:
- The specific data point or finding
- The source (name, date, URL where possible)
- The confidence score (CS-1 / CS-2 / CS-3 / CS-4) per the Confidence Scoring Scale in research-source-guide.md. CS-1 = company-reported results, executive quotes, top-tier analysts, government data. CS-2 = reputable independent research, business press of record, expert interviews. CS-3 = news articles, vendor reports, press releases (corroboration required). CS-4 = blog posts, opinion pieces, social media (do not use as evidence).
- Whether this supports, undermines, or is neutral to the hypothesis
-
Explicitly flag:
- Information gaps: what you looked for but could not find publicly
- Contradictions: where sources disagree with each other
- Stale data: findings older than 2 years that may no longer hold
- Private information needed: data that likely exists only inside the client organization or behind paywalls, and what expert interviews might unlock
- Risks and failure modes: what could go wrong if the client acts on the hypothesis
-
For every case study, cautionary tale, or benchmark you cite, extract ALL lessons — not just the most obvious one. Systematically ask: "What are ALL the lessons this example teaches?" A single example often contains multiple independent insights. Probe each example for at least 2-3 takeaways. For instance, a company's failed market entry teaches not only "the market was too competitive" but also "the timing was wrong relative to regulatory changes" and "the go-to-market team lacked local expertise."
-
Collect industry-specific terminology: as you research, note the standard terms, jargon, and acronyms that practitioners and industry participants use. Record them in the Industry Terminology section of your output.
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 · 130 lines · 215 tokens per session scan A 557346e6303e
analyst-bravo is an agent published in the GitHub repository ChipAlexandru/strategy-consultant (4 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 215 tokens to every session and 1,714 once invoked, about $0.0011 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 agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
Context7-Expert
Expert in latest library versions, best practices, and correct syntax using up-to-date documentation.
Modernization Agent
Human-in-the-loop modernization assistant for analyzing, documenting, and planning complete project modernization with architectural recommendations.