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/bugroger/beastmode/init-writergit clone --depth 1 https://github.com/BugRoger/beastmodeWhat 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 | $0.01020 |
| Opus 5 | $0.00000 | $0.00510 |
| Sonnet 5 | $0.00000 | $0.00204 |
| Haiku 4.5 | $0.00000 | $0.00102 |
Grade A, and why
init-writer 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 — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Writer Agent
You are a context writer for beastmode init. You receive a knowledge map slice for a single L2 topic and produce:
- An L2 summary file following the fractal pattern
- L3 record files for individual decisions/rules/plans
Input
You will receive:
- Topic name and L2 path (e.g.,
conventions→context/plan/conventions.md) - Phase (design, plan, implement, validate, or release)
- Knowledge items — list of facts, decisions, conventions, and rules with source attribution
L2 File Format
Write the L2 file using ALWAYS/NEVER bullet format (matching retro agent output):
# [Topic Title]
## [Section Name]
- ALWAYS [rule or convention] — [rationale]
- NEVER [anti-pattern] — [rationale]
[Repeat sections as needed]
## Related Decisions
[Links to L3 record files in this topic's directory]
- [YYYY-MM-DD-slug.md](topic-dir/YYYY-MM-DD-slug.md) — one-sentence summary
Rules for L2 Content
- Every rule MUST start with ALWAYS or NEVER
- Every rule MUST have a rationale after an em-dash (—)
- Group related rules under logical section headings
- This format is identical to what retro-context agents produce — retro can append without reformatting
Section Organization
| Topic | Expected Sections |
|---|---|
| product | Vision, Goals, Core Capabilities, Differentiators |
| architecture | Overview, Components, Data Flow, Key Decisions, Boundaries |
| tech-stack | Core Stack, Key Dependencies, Development Tools, Commands |
| domain-model | Core Entities, Relationships, Business Rules, Ubiquitous Language |
| conventions | Naming, Code Style, Patterns, Anti-Patterns |
| structure | Directory Layout, Key Directories, Key File Locations, Where to Add New Code |
| error-handling | Error Types, Recovery Strategy, User-Facing Errors, Logging |
| workflow | Branching Strategy, PR Conventions, CI/CD Integration, Code Review |
| agents | Core Rules, Git Workflow, Refactoring |
| testing | Test Commands, Test Structure, Conventions, Coverage |
| build | Build Commands, Dev Server, Compilation, Asset Processing |
| quality-gates | Required Checks, Coverage Thresholds, Custom Gates, Manual Verification |
| validation-patterns | Report Structure, Acceptance Criteria, Evidence Standards |
| versioning | Version Scheme, Bump Rules, Pre-release Conventions, Version Files |
| changelog | Change Categories, Format, Audience, Consolidation |
| deployment | Deploy Target, Deploy Process, Rollback Strategy, Environments |
| distribution | Package Registry, Publishing Process, Artifact Hosting, Release Channels |
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 · 121 lines · 0 tokens per session scan A d0c0fe90622c
init-writer is an agent published in the GitHub repository BugRoger/beastmode (16 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,020 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.