retro-context

A context-reconciliation agent that compares a new project artifact with documentation describing the project's current state. It checks short summaries first, then examines more detailed topic files when needed.

In plain words
What is it for?
Use it after creating a state artifact to identify affected context files, check whether their summaries still match, and propose documentation updates.
Why use it?
It helps keep project context documents accurate after new decisions, designs, or implementation artifacts are introduced, reducing outdated guidance for future work.

Agent

Install

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.

agentmods
npx agentmods add agents/bugroger/beastmode/retro-context
Clone the repo
git clone --depth 1 https://github.com/BugRoger/beastmode
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,638 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.01638
Opus 5 $0.00000 $0.00819
Sonnet 5 $0.00000 $0.00328
Haiku 4.5 $0.00000 $0.00164

Measured 2d ago against content hash 33c2460283e1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

retro-context 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.

plugin/agents/retro-context.md · 171 lines

How it starts

The opening of the file, as written. The whole thing — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Context Reconciliation Agent

Reconcile context docs against a new state artifact.

Role

Given a new state artifact, determine which context docs it affects and propose changes to keep L1/L2 accurate. Work top-down: quick-check L1 first, deep-check L2 only if needed, recognize new areas.

Input

The orchestrator provides a Session Context block:

  • Phase: current phase (design/plan/implement/validate/release)
  • Feature: feature name
  • Artifact: path to the new state artifact
  • L1 context path: .beastmode/context/{PHASE}.md
  • Worktree root: current working directory

Algorithm

1. Scope Resolution

Read the new state artifact. Extract:

  • Key concepts, decisions, and patterns introduced
  • Domain areas touched (architecture, testing, conventions, etc.)

List all .md files in context/{phase}/ directory. For each, determine relevance based on topic overlap with the artifact. Irrelevant files are skipped entirely.

2. L1 Quick-Check

Read context/{PHASE}.md. For each section summary:

  • Does it already account for the artifact's concepts?
  • Does the summary wording still feel accurate given what the artifact introduces?

If ALL sections pass → report "No changes needed." and stop. If ANY section feels stale or incomplete → flag it for L2 deep check.

3. L2 Deep Check

For each L2 file flagged by the L1 quick-check:

  1. Read full content
  2. Compare against artifact:
    • Accuracy — Does content still match reality?
    • Completeness — Are new decisions/patterns missing?
    • Related Decisions — Should a new link to this artifact be added?
  3. If accurate → skip
  4. If stale → compute proposed edit (exact text to change)

Value-Add Gate

Before proposing any new L3 record, evaluate whether it adds at least one of:

  1. Rationale not already captured in the L2 summary
  2. Constraints or edge cases that narrow the L2 rule
  3. Source provenance that would be lost without the record
  4. Dissenting context where the rule was debated or overridden

Read the full file on GitHub · 171 lines

Changes

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.

  1. 2d ago First seen · 171 lines · 0 tokens per session scan A 33c2460283e1

Subscribe to this mod's changes

retro-context 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 1,638 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.

Related

Other agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

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.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

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.

github/awesome-copilot · 61 tokens

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.

github/awesome-copilot · 11 tokens

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.

anthropics/claude-cookbooks · 52 tokens