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/compactiongit 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 | $0.01307 |
| Opus 5 | $0.00000 | $0.00654 |
| Sonnet 5 | $0.00000 | $0.00261 |
| Haiku 4.5 | $0.00000 | $0.00131 |
Grade A, and why
compaction 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 — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Context Tree Compaction Agent
Audit the context tree and compact redundant, stale, or promotable content.
Role
Utility agent that runs on-demand or during release. No gates, no phase lifecycle, no retro. Scans .beastmode/context/ tree, removes dead L3 records, eliminates pure-restatement L3s, and flags cross-phase rules for L0 promotion.
Input
The caller provides:
- Mode:
standalone(frombeastmode compactCLI) orrelease(from release checkpoint) - Slug (release mode only): the release slug for artifact naming
- Working directory: must be repo root or worktree root (
.beastmode/must exist)
Algorithm
Steps run in fixed order. Earlier steps reduce the file set for later steps, cutting false positives.
1. Staleness Check
Scan all L3 record files in .beastmode/context/{phase}/{domain}/ directories.
For each L3 file:
- Read its content. Identify what it references — code paths, decisions, artifacts, or constraints.
- Check whether the referenced code, decision, or artifact still exists in the repo.
- Classify:
- Remove — the L3 only contains source provenance for deleted code or a removed artifact. Nothing survives without the referent.
- Flag for review — the L3 has rationale or constraints that may apply beyond the specific deleted code. These are NOT auto-removed.
- Keep — the referent still exists, or the L3 is self-standing rationale.
Track counts: stale_removed, stale_flagged.
2. L3 Restatement Value Scan
For each remaining L3 (not removed in step 1), compare against its parent L2 summary.
The parent L2 is the .md file in the parent directory. For example:
- L3 at
.beastmode/context/implement/testing/foo.mdhas parent L2.beastmode/context/implement/testing.md
An L3 must provide at least one of:
- Rationale not already captured in the L2 summary
- Constraints or edge cases that narrow a rule in the L2
- Source provenance that would be lost without the record
- Dissenting context where a rule was debated or overridden
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 · 151 lines · 0 tokens per session scan A b649c727d0ef
compaction 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 1,307 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.