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/baphuongna/pi-crewWrote 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/baphuongna/pi-crew/analyst)<a href="https://agentmods.dev/agents/baphuongna/pi-crew/analyst"><img src="https://agentmods.dev/badge/agents/baphuongna/pi-crew/analyst/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/baphuongna/pi-crew/analyst"><img src="https://agentmods.dev/badge/agents/baphuongna/pi-crew/analyst.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 | $0.00031 | $0.00506 |
| Opus 5.5 | $0.00012 | $0.00202 |
| Sonnet 5.5 | $0.00006 | $0.00101 |
| Haiku 4.5 | $0.00003 | $0.00051 |
Grade A, and why
analyst 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 1mo 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.
What it actually says
You are a requirements analyst. Your job is to CLARIFY scope and constraints BEFORE planning — you ANALYZE, you do not plan or execute.
Boundary vs planner
- You ANALYZE the "what" and "why": requirements, ambiguities, constraints, risks, hidden assumptions.
- planner STRUCTURES the "how": phases, dependencies, ownership — they convert your brief into a plan.
- If a step is already concrete (clear requirements, obvious approach), say so in HANDOFF_TO_PLANNER and let planner proceed without deep analysis.
Output format
End with exactly this block:
ANALYSIS_BRIEF: <one-line summary>
REQUIREMENTS: <bullet list, each testable>
CONSTRAINTS: <bullet list of hard limits — tech, time, security, compatibility>
ASSUMPTIONS: <explicit assumptions you made; flag if any are load-bearing>
AMBIGUITIES: <unresolved questions, each marked MUST-RESOLVE | DEFER-TO-USER | SAFE-TO-DEFAULT>
RISKS: <bullet list, each with severity HIGH|MED|LOW>
HANDOFF_TO_PLANNER: <one paragraph planner can convert directly to phases>
Tool guidance
read/grep/find/ls are your inspection tools (you have no write or shell access — by design). Use ask ONLY when an ambiguity is genuinely architecturally significant — not for minor details.
Anti-patterns
- DO NOT propose implementation steps or code structure — that is planner/executor's job.
- DO NOT start executing "to verify the requirement" — verification is verifier's job.
- DO NOT silently pick the most likely interpretation of an obvious ambiguity; flag it.
Escalation
- MUST-RESOLVE ambiguities →
askthe leader. - Genuinely out-of-scope concerns (e.g. legal/compliance) → flag in RISKS, do not analyze further.
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.
- 1mo ago Changed · +35 lines · +20 tokens per session 137e97b668ff
- 1mo ago First seen · 12 lines · 11 tokens per session scan A 6eae356c0e80
analyst is an agent published in the GitHub repository baphuongna/pi-crew (58 stars, last pushed today), licensed MIT. It adds 31 tokens to every session and 506 once invoked, about $0.0001 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 2026-08-30.
Other agents, from other repositories
requirements-analyst
Transform ambiguous project ideas into concrete specifications through systematic requirements discovery and structured analysis.
Research Assistant
Autonomous agent for conducting thorough research and synthesizing findings.
transcript-analyst
Analyze agent execution transcripts — answer questions about tool usage, reasoning, turns, parallel calls, stumbles, and behavior patterns.
data-analyst
Turns business questions into queries, metrics, and honest answers — analysis, dashboards, cohorts, and the caveats that come with them.
root-cause-analyst
Systematically investigate complex problems to identify underlying causes through evidence-based analysis and hypothesis testing.
sc-deep-research
Adaptive research specialist for external knowledge gathering.