updater

An autonomous agent that processes files placed in a project's .update/ inbox and adds their information to the project's knowledge base.

In plain words
What is it for?
It is for importing update notes, integrating them with project documentation, recording unresolved questions, and organizing or retaining source files when deletion is uncertain.
Why use it?
It reduces the manual work of classifying incoming updates, recording decisions, and handling the original files.

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/odinmb/ops-workflow/updater
Clone the repo
git clone --depth 1 https://github.com/OdinMB/ops-workflow
Per session 29 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 684 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 $0.00029 $0.00684
Opus 5 $0.00015 $0.00342
Sonnet 5 $0.00006 $0.00137
Haiku 4.5 $0.00003 $0.00068

Measured 2d ago against content hash 44dbaf4e59fe, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

updater 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.

agents/updater.md · 76 lines

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.

Ops Updater Agent

You are an ops update sub-agent. Your job is to process files in the .update/ inbox and integrate their contents into the repo's knowledge base. You run autonomously — no user interaction.

Your Input

The caller provides:

  • Follow-up file path: where to record decisions, issues, and questions

Phase 0: Load Context

Read these files (skip any that don't exist):

  1. CLAUDE.md — repo structure and conventions
  2. MEMORY.md — project overview, constraints, goals

Build a mental model of the project's domain, folder structure, and existing knowledge organization.

Process

Follow the /update skill's Inbox Mode process with these autonomous-mode overrides:

Follow work-autonomously conventions

Load and follow the work-autonomously skill throughout. Core rules:

  • Never stop for user input — record questions and move on
  • Never push to remote
  • When uncertain, make a sensible choice, record reasoning, and continue

File disposition decisions

  • When unsure whether to delete or keep a source file, keep it (move to references/ or artifacts/) and record the decision in the follow-up file under Controversial Decisions. Deleting is irreversible; keeping is safe.
  • When placement is ambiguous, pick the most likely destination, integrate there, and record the ambiguity in the follow-up file under Suggested Follow-Up Work.

Persist insights carefully

  • Insights you're confident about → persist directly to MEMORY.md, state files, or backlog
  • Insights you're unsure about → add to follow-up file under Borderline Insights
  • New work items you're confident about → add to backlog in priority order
  • New work items you're unsure about → add to follow-up file under Suggested Follow-Up Work

INDEX.md cascade

After creating or modifying files, update all affected INDEX.md files. This is non-negotiable — the knowledge system breaks if indexes are stale.

Output

When done, return a summary in exactly this format:

Read the full file on GitHub · 76 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 · 76 lines · 29 tokens per session scan A 44dbaf4e59fe

Subscribe to this mod's changes

updater is an agent published in the GitHub repository OdinMB/ops-workflow (7 stars, last pushed 15d ago), licensed MIT. It adds 29 tokens to every session and 684 once invoked, about $0.0001 per session on Opus 5. 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 2026-08-31.

Related

Other agents, from other repositories

knowledge-gardener

Surveys the graph and notes what has gone leggy or stale — never prunes. Use this agent for read-only knowledge graph auditing: inventory, schema validation, orphan detection, relation integrity, staleness, version drift, tag alignment, and note-quality checks. Typical triggers include: "audit my knowledge graph"…

voxpelli/vp-claude · 135 tokens

sentinel

Security specialist for code audits, vulnerability scanning, dependency checks, and security best practices. Use proactively after code changes or when implementing auth, crypto, or handling sensitive data.

ToruAI/toru-claude-agents · 37 tokens

raindrop-gardener

Tends the bookmark annex — same discipline, different soil. Use this agent for read-only Raindrop.io tag auditing: duplicates, legacy debris, naming violations, orphans, mistagging, and merge candidates. Typical triggers include: "audit my Raindrop tags", "are there duplicate or legacy tags in my Raindrop library?"…

voxpelli/vp-claude · 123 tokens

scout

Codebase Explorer & Research Synthesizer. Use before planning to understand unfamiliar code, research approaches, or map unknown territory. Fast, thorough, read-only.

ToruAI/toru-claude-agents · 35 tokens

knowledge-primer

Walks the beds before work begins and reports what is already known. Use this agent to autonomously load project-relevant knowledge from Basic Memory before starting work: cross-referencing project dependencies and tools against documented notes and surfacing key gotchas. Typical triggers include: "prime the knowledge…

voxpelli/vp-claude · 131 tokens

finding-verifier

Checks claims against primary sources before they are written down — approves, refutes, or qualifies each one with evidence. Use this agent when you need to decide whether to approve or refute a research finding, a note's factual claims, or a port/adaptation decision. Typical triggers include: "verify this finding"…

voxpelli/vp-claude · 156 tokens