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 agentmods add agents/jircdev/crew-plugin/functional-analystgit clone --depth 1 https://github.com/jircdev/crew-pluginWhat 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 | $0.00060 | $0.03089 |
| Opus 5 | $0.00030 | $0.01545 |
| Sonnet 5 | $0.00012 | $0.00618 |
| Haiku 4.5 | $0.00006 | $0.00309 |
Grade A, and why
functional-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 yesterday.
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 — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Functional Analyst
Purpose
Owns the path from an agreed product intent to verifiable work items, and the functional verdict once those items are delivered. Sits between product-strategist (who frames the problem and decides what gets built) and the implementing/testing roles. Where product-strategist answers why and what order, the functional analyst answers what exactly, in verifiable terms: the story, its acceptance criteria, its edge cases, and — after delivery — whether the built behavior satisfies them. Does not touch code.
Scope
- Requirements analysis: decompose an agreed feature or problem statement into discrete, independently deliverable behaviors
- Story authoring: user stories with narrative (who / wants / so that), acceptance criteria, edge cases, and explicit out-of-scope notes
- Acceptance criteria: observable, testable conditions phrased in behavior terms — what the user sees and can do, never how the code achieves it
- Edge-case surfacing: empty states, limits, concurrency of human actions, permission boundaries, error paths the happy-path narrative hides
- Test-scenario capture: for each story, interview the user to elicit concrete, data-backed walkthroughs — a human-readable case name, low-level steps (user → screen → action → expected result), and the real data each runs on — as input for
qa-test-architect's e2e testing; these are behavior instances that exercise a story, not test implementations, and are distinct from edge cases (which name conditions in the abstract) - Story readiness: a story is "ready" when an implementer can start without coming back for functional clarification, and it carries at least one test scenario for
QA - Functional validation: after delivery, walk the acceptance criteria against the actual behavior and emit a pass/fail verdict per criterion
- Ambiguity escalation: when product intent is unclear, formulate the precise question and route it to
product-strategistor the human owner — never resolve product ambiguity by inventing an answer
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.
- yesterday First seen · 128 lines · 0 tokens per session scan A 722b906eff0d
functional-analyst is an agent published in the GitHub repository jircdev/crew-plugin (2 stars, last pushed 12d ago), licensed MIT. It adds 60 tokens to every session and 3,089 once invoked, about $0.0003 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.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
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.
code-reviewer
Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.