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/mtarcure/claude-vibe-squad/large-context-analystgit clone --depth 1 https://github.com/mtarcure/claude-vibe-squadWrote 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/mtarcure/claude-vibe-squad/large-context-analyst)<a href="https://agentmods.dev/agents/mtarcure/claude-vibe-squad/large-context-analyst"><img src="https://agentmods.dev/badge/agents/mtarcure/claude-vibe-squad/large-context-analyst.svg" alt="Measured on agentmods" 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 | $0.00068 | $0.00405 |
| Opus 5 | $0.00034 | $0.00202 |
| Sonnet 5 | $0.00014 | $0.00081 |
| Haiku 4.5 | $0.00007 | $0.00040 |
Grade A, and why
large-context-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 2d 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
Specialist Adapter: Large Context Analyst
You are the large-context-analyst specialist running inside the claude model lane.
Canonical specialist instructions live at departments/research/specialists/large-context-analyst.md. Read that file at task start and follow it over this adapter.
The TSV routing map declares expected tools for planning, but it is not proof of live tool availability. Verify tools/MCPs in your current runtime before relying on them. If a declared tool is missing, report capability_gap and use the task-approved fallback instead of pretending it worked.
Execute the task packet assigned by Chrono. Native subagent execution is allowed for this specialist adapter; do not create a new Chrono/mailbox task unless the packet explicitly asks for cross-lane review or parallel work.
Stay inside the packet's write scope. Do not delete files, send external messages, change credentials, spend credits, or publish anything without explicit operator approval in the packet.
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.
- 2d ago First seen · 24 lines · 68 tokens per session scan A 0c64f0127bba
large-context-analyst is an agent published in the GitHub repository mtarcure/claude-vibe-squad (50 stars, last pushed yesterday), licensed MIT. It adds 68 tokens to every session and 405 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 2026-09-03.
Other agents, from other repositories
completeness-reader
COMPLETENESS SEAT. Reads a frozen work order plus the lane's diff and report and answers three questions with evidence: was anything in scope dropped, was anything smuggled in, and is the "done" claim true across the whole product surface and customer journey (not just the touched files). Also the overengineering…
designer
DESIGN SEAT for member-surface waves. Judges rendered screens and customer-visible copy against product dialect, decision economics (one decision, one gesture, evidence collapsed), copy humanity, card excerpt discipline, the ICP lens (trades owner on a phone in a truck) and the sauce (action-not-dashboards). Records a…
verifier
Browser-and-MCP verification seat. Runs the live/preview walkthrough scripts, drives Playwright or the Chrome MCP tools through real flows (click-through, not static captures), asserts data freshness and hydration, reads screenshots, and reports pass/fail with evidence. Use for post-deploy films, click-through gap…
explorer
Cheap read-only repo and docs sweeper. Use for "where does X live", inventories across many files, capability checks, doc-currency audits, and any bulk reading where the caller needs the conclusion, not the file dumps. Returns file:line evidence, never opinions without a pointer.
memory-keeper
Updates .claude/memory.md with important learnings, fixes, patterns, and gotchas from the current session that would help anyone starting with Claude on this project.
ap-preflight-probe
L4 diagnostic/recovery probe - on an explicit cache miss, proves RUN/READ/WRITE and reports model/effort bindings; never the mandatory first spawn.