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/readmegit 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 | $0.01234 |
| Opus 5 | $0.00000 | $0.00617 |
| Sonnet 5 | $0.00000 | $0.00247 |
| Haiku 4.5 | $0.00000 | $0.00123 |
Grade A, and why
README 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 — 67 lines — stays where its author put it; the contents beside it link to each section on GitHub.
[!NOTE] This README was AI-generated. I (Angadh) have not manually authored this nor checked it.
Agents — Planner's Menu
Fourteen agents forming the Botference loop. Each reads checkpoint.md, produces outputs, updates checkpoint, and yields.
All agents inherit shared protocol from agent-base.md.
Custom workspace agents (in project .claude/agents/) override framework agents of the same name and declare their tools in a ## Tools section.
Agent Reference
| Agent | Role | Tools (beyond essentials) | Upstream → | → Downstream | Assign when… |
|---|---|---|---|---|---|
| scout | Search + score papers | pdf_metadata, citation_lookup/verify/verify_all, citation_manifest/download, validate_paper_ledger, render_paper_ledger_markdown, validate_support_requests | user/planner | triage | Starting literature search or filling gaps |
| triage | Dedup corpus, resolve grade conflicts, generate reading plan | pdf_metadata, citation_verify_all, validate_paper_ledger, render_paper_ledger_markdown | scout | deep-reader | After scout completes a round |
| deep-reader | Read PDFs, extract claims/data, map sections | pdf_metadata, extract_figure, validate_paper_ledger, render_paper_ledger_markdown, validate_support_requests | triage | critic, provocateur, synthesizer | After triage produces a reading plan |
| critic | Assess structure; check style/journal/figure compliance; propose figures | check_language, check_journal, check_figure, check_claims, citation_verify_all | deep-reader (survey), paper-writer (STYLE-CHECK), editor (compliance) | provocateur, synthesizer (survey); paper-writer (STYLE-CHECK); research-coder (FIGURE-PROPOSAL) | After deep-reader finishes, or after each paper-writer section |
| provocateur | Stress-test: negative space, inverted assumptions, cross-domain bridges | — | deep-reader + critic | synthesizer | After critic's survey assessment |
| synthesizer | Merge findings into synthesis narrative + outline | citation_lint, citation_verify_all | deep-reader + critic + provocateur | paper-writer | After all analysis agents complete |
| paper-writer | Write/revise sections; review editor changes | check_language, citation_lint, validate_support_requests | synthesizer (write), critic (revise), editor (REVIEW-EDITS) | critic (STYLE-CHECK), editor | When outline is ready or revisions approved |
| editor | Substantiated edits to .tex with evidence backing | check_claims, check_language, citation_lint, citation_verify_all | paper-writer | coherence-reviewer, paper-writer (REVIEW-EDITS) | After paper-writer completes a section |
| coherence-reviewer | Post-editing: promise-delivery, terminology, contradictions, novelty claims | check_claims, check_language | editor | editor (fixes) | After all sections are edited |
| research-coder | Analysis scripts, simulations, figures from data | — | critic (FIGURE-PROPOSAL), planner | figure-stylist (figures), paper-writer (data) | When figures proposed or data analysis needed |
| figure-stylist | Visual clarity + print readiness review | check_figure | research-coder | research-coder (revise) or next phase | After each figure is generated |
| coder | Read, modify, and test application code | — | planner | planner (task complete) | When implementation tasks require source code changes |
| refactorer | Restructure code to reduce duplication | — | planner | planner (task complete) | When task says "refactor" |
| orchestrator | AI-driven dispatch at phase boundaries | read_file, list_files | planner | parallel/serial agents | When Architecture is orchestrated |
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 · 67 lines · 0 tokens per session scan A aef691bdbef5
README is an agent published in the GitHub repository angadhn/botference (19 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,234 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.