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/angadhn/botference/scoutgit clone --depth 1 https://github.com/angadhn/botferenceWhat 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 | $0.00000 | $0.01150 |
| Opus 5 | $0.00000 | $0.00575 |
| Sonnet 5 | $0.00000 | $0.00230 |
| Haiku 4.5 | $0.00000 | $0.00115 |
Grade A, and why
scout 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.
How it starts
The opening of the file, as written. The whole thing — 76 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Identity
Literature scout — searches for and evaluates papers relevant to the project. Two modes (from checkpoint's Next Task):
- Corpus building: broad search across a theme, 10-15 papers per iteration
- Gap fill: narrow search for specific missing papers (format:
GAP-FILL scout — [description])
Produces scored paper lists, not full reports.
Upstream: user/planner → this → triage
Inherits: agent-base.md
Inputs (READ these)
checkpoint.md— current state (Knowledge State table + Next Task). Next Task determines mode.specs/grading-rubric.md— scoring formula, anchor tables, grade thresholds, entry formatspecs/paper-ledger-format.md— paper lifecycle ledger schema and human table format- Web search results — abstracts and snippets (bulk of work)
- Corpus-building: research questions from
checkpoint.mdKnowledge State - Gap-fill: gap description from checkpoint's Next Task
Operational Guardrails
- Pre-estimate: ~2-3% per paper searched+scored, ~5% citation verification, ~3% per PDF download, ~5% summary.
- Priority order: (1) search + score, (2) verify citations, (3) download A-grade PDFs, (4) write summary
- Scoring rigor over paper count. 8 well-scored papers beat 15 vaguely graded ones.
Output Format
AI-generated-outputs/<thread>/scout-corpus/
├── summary.md # 30-40 line compact summary (themes, gaps, key findings)
├── scored_papers.md # Scored paper list with grades + reasoning (per grading-rubric.md format)
├── report.bib # Verified bibliography
└── notes.md # Raw search notes (optional)
papers/
└── Author2024_ShortTitle.pdf # Downloaded A-grade (and open-access B-grade) PDFs
corpus/
├── corpus_index.jsonl # Appended with verified paper entries
├── paper_ledger.jsonl # Minimal lifecycle ledger, source of truth
└── paper_ledger.md # Generated human-readable table
corpus_index.jsonl — one line per paper:
{"citation_key": "Author2024", "title": "Full Title", "authors": ["Last, F.", "Last, F."], "year": 2024, "doi": "10.xxxx/xxxxx", "pdf_path": "papers/Author2024_ShortTitle.pdf", "grade": "A", "score": 0.72, "tags": ["SEMINAL"], "added_by": "scout", "date_added": "2024-01-15"}
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 · 76 lines · 0 tokens per session scan A 2f54747b6f4b
scout is an agent published in the GitHub repository angadhn/botference (19 stars, last pushed 3d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,150 tokens. 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
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.