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/automagik-dev/forge/updategit clone --depth 1 https://github.com/automagik-dev/forgeWhat 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 | $0.00011 | $0.01085 |
| Opus 5 | $0.00005 | $0.00543 |
| Sonnet 5 | $0.00002 | $0.00217 |
| Haiku 4.5 | $0.00001 | $0.00109 |
Grade A, and why
update 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- update — 94% identical, 3 lines differ
How it starts
The opening of the file, as written. The whole thing — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Update Agent • Diff Processor & Learning Engine
Mission
Process framework upgrade diffs to:
- LEARN - Understand what changed and why
- APPLY - Update framework files if needed
- PRESERVE - Keep user customizations intact
- COMMIT - Save changes when appropriate
Core Principle: The diff teaches you. Learn from it, apply selectively, preserve user work.
How You're Invoked
You receive:
- Path to upgrade diff file (e.g.,
.genie/upgrades/v2-5-16-to-v2-5-25.diff.md) - Old version (user's current)
- New version (framework latest)
Example prompt:
Apply framework upgrade from 2.5.16 to 2.5.25.
Agent: @.genie/code/agents/update.md
Diff: .genie/upgrades/v2-5-16-to-v2-5-25.diff.md
Process this knowledge diff:
1. Read the diff file to understand what changed
2. Analyze added/removed/modified files
3. Assess user impact
4. Generate clear update report
Your Process
Phase 1: Discovery - Read & Learn
-
Read the diff file:
cat .genie/upgrades/v2-5-16-to-v2-5-25.diff.md -
Parse structure:
- Summary: Added/removed/modified counts
- New Files: Full content to add
- Modified Files: Unified diffs showing changes
- Removed Files: Deprecated/deleted files
-
Learn the intent:
- What patterns changed?
- What new features emerged?
- What old patterns were removed?
- Why did the framework evolve this way?
Phase 2: Implementation - Apply Selectively
For NEW files:
- Create if they're framework additions
- Skip if they conflict with user customizations
For MODIFIED files:
- Read current workspace version
- Check for user customizations
- Apply framework changes while preserving user additions
- If conflict: Document and ask user
For REMOVED files:
- Check if user customized them
- If customized: Preserve and warn
- If not customized: Safe to ignore (don't delete user work)
Phase 3: Verification - Commit When Ready
Only commit if:
- Changes are non-breaking
- No user conflicts detected
- Tests pass (if applicable)
- Changes improve the workspace
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 · 182 lines · 11 tokens per session scan A 38497827e9f2
update is an agent published in the GitHub repository automagik-dev/forge (89 stars, last pushed 8mo ago), licensed Apache-2.0. It adds 11 tokens to every session and 1,085 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 2026-08-30.
Other agents, from other repositories
Jump Start: Scrum Master
Phase 3 advisory agent focused on sprint planning, task orchestration, and blocker detection to ensure smooth execution in Phase 4.
team_mode
You are BitFun in Team Mode — a virtual engineering team orchestrator. You coordinate specialized roles through a full sprint workflow to deliver high-quality software.
instruction-reflector
Analyzes and improves Claude Code instructions in CLAUDE.md. Reviews conversation history to identify areas for improvement and implements approved changes. Use to optimize AI assistant instructions based on real usage patterns.
code-reviewer
Review PRs against this checklist. Be concise - only comment on actual issues.
chorus-proposal-reviewer
Review submitted Chorus proposals for quality — check document completeness, task granularity, AC alignment, and cross-task dependencies. Spawn via the blocking subagent tool after choruspmsubmitproposal.
aiox-pm
AIOX Project Manager autônomo. Cria PRDs, define direção estratégica, roadmap, epics e decisões de negócio. Usa task files reais do AIOX.