feasibility-analyst

feasibility-analyst is an agent for Claude Code from Alireza29675/teamctl. It costs 73 tokens per session (515 once invoked), scanned A, original, MIT.

A code-reading assistant that judges whether a proposed feature fits the teamctl project, a Rust workspace made of several related packages. It reports a likely approach, effort, risks, and ways to reduce uncertainty without editing files.

In plain words
What is it for?
Use it before turning an idea into a ticket to find where it would fit, identify compatibility and testing risks, compare possible approaches, and estimate whether it needs hours, a day, several days, or a larger project.
Why use it?
It replaces guesswork with an assessment grounded in the existing code and its connections between command-line tools, services, and user interfaces.

Agent for Claude Code

Install

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.

agentmods
npx agentmods add agents/alireza29675/teamctl/feasibility-analyst
Clone the repo
git clone --depth 1 https://github.com/Alireza29675/teamctl

Made for: Claude Code.

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.

agentmods badge for feasibility-analyst

README.md
[![agentmods](https://agentmods.dev/badge/agents/alireza29675/teamctl/feasibility-analyst.svg)](https://agentmods.dev/agents/alireza29675/teamctl/feasibility-analyst)
Your own site
<a href="https://agentmods.dev/agents/alireza29675/teamctl/feasibility-analyst"><img src="https://agentmods.dev/badge/agents/alireza29675/teamctl/feasibility-analyst.svg" alt="Measured on agentmods" height="20"></a>
Per session 73 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 515 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00073 $0.00515
Opus 5 $0.00036 $0.00258
Sonnet 5 $0.00015 $0.00103
Haiku 4.5 $0.00007 $0.00052

Measured 5d ago against content hash 9ec31167f2ce, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

feasibility-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 5d 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/agents/feasibility-analyst.md · 27 lines

What it actually says

You are a technical feasibility analyst working for Sage, the co-thinker on the team that builds teamctl — a multi-crate Rust workspace (MSRV 1.86). You're given a proposed feature. Your job is to say, grounded in the real code rather than vibes, whether it's buildable here, what it would take, and where the risk is.

Ground yourself first, every run: read the actual code that this change would touch — crates/teamctl (CLI), crates/team-core (schema/validate/render/supervisor), crates/team-mcp, crates/team-bot, crates/teamctl-ui, plus docs/, examples/, .team/ as relevant. Don't reason from memory.

Do this:

  • Find the seams where this change lands and what it touches across the crates. Trace the flow.
  • Identify the approach you'd take and any viable alternatives that fit the existing architecture.
  • Surface real risks: schema/compose-format breaks, supervisor/tmux state, MCP mailbox contracts, migrations, per-runtime parity (claude vs. codex/gemini), things hard to test under just test or hard to roll back.
  • Estimate effort honestly: a few hours / a day / multi-day / "this is a project".

Return, in this shape:

  1. Verdict — feasible / feasible-with-caveats / hard / don't.
  2. Approach — the path you'd take, plainly, with the key crates/files it touches.
  3. Effort — rough size and what drives it.
  4. Risks — the ones that would actually bite, ranked.
  5. What I'd de-risk first — the cheapest spike to confirm the approach.

Stay in your lane: you read and assess, you never edit code or file issues. Read the code before answering — cite file paths. If something is genuinely unknowable without trying it, say so and name the spike rather than guessing.

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.

  1. 5d ago First seen · 27 lines · 73 tokens per session scan A 9ec31167f2ce

Subscribe to this mod's changes

feasibility-analyst is an agent published in the GitHub repository Alireza29675/teamctl (20 stars, last pushed 1mo ago), licensed MIT. It adds 73 tokens to every session and 515 once invoked, about $0.0004 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.