Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/rumotion/ai-agent-project-templatenpx agentmods add skills/rumotion/ai-agent-project-template/project-upgraderWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/rumotion/ai-agent-project-template/project-upgrader)<a href="https://agentmods.dev/skills/rumotion/ai-agent-project-template/project-upgrader"><img src="https://agentmods.dev/badge/skills/rumotion/ai-agent-project-template/project-upgrader/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/rumotion/ai-agent-project-template/project-upgrader"><img src="https://agentmods.dev/badge/skills/rumotion/ai-agent-project-template/project-upgrader.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00070 | $0.00872 |
| Opus 5 | $0.00035 | $0.00436 |
| Sonnet 5 | $0.00014 | $0.00174 |
| Haiku 4.5 | $0.00007 | $0.00087 |
Grade A, and why
project-upgrader 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 9d 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.
How it starts
The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Upgrader Skill
Use this skill whenever asked to upgrade an existing repository/project using the latest version of the AI Agent Project Template.
Core Directives
[!IMPORTANT]
- Zero Damage to Existing Project Domain Code: Never overwrite, delete, or alter custom application code, test scripts (
test_*.py,*.spec.ts, etc.), project assets, extraction logic, authentication configs (*.json,.env), or custom domain skills (e.g.,kumo-canvas).- Preserve Custom AGENTS.md Rules: Always retain project-specific domain rules found in the target repository's
AGENTS.md(e.g. database safety rules, test board rules).- Context Budget Enforcement: Ensure target
AGENTS.mdstays <= 6,500 chars andmemory-bank/handoff.mdstays <= 1,200 chars to satisfyFAST_INITbudget checks.
Upgrade Execution Procedure
Step 1: Preflight & Dry-Run
- Identify target project path (e.g.
c:\AI\_code\InnovationLab\KUMO\KumoQAToolkit). - Run a dry-run to preview planned modifications:
python scripts/upgrade-target.py --target <target-path> --dry-run - Read target
AGENTS.mdand.agents/skills/to verify custom domain rules and custom domain skills to preserve.
Step 2: Automated Framework Upgrade
- Execute the automated upgrade tool:
This automatically:python scripts/upgrade-target.py --target <target-path>- Preserves custom domain rules in
AGENTS.mdwhile merging latest canonical instructions, falsifiable predictions, escalation ladder, and bimodal execution. - Synchronizes multi-agent adapters (
GEMINI.md,CLAUDE.md,CONVENTIONS.md,.windsurfrules,.codex/AGENTS.md,.cursor/rules/agents.mdc,.github/copilot-instructions.md,.clinerules/,.agents/rules/). - Synchronizes 10 workflows across
workflows/,.agents/workflows/,.clinerules/workflows/. - Synchronizes standard skills across
.agents/skills/,.claude/skills/,.cline/skills/while preserving custom domain skills intact. - Copies safety hooks, reviewer contracts, documentation, and validation scripts (
scripts/check-template.py,scripts/init-fast.py,scripts/detach-remote.py,scripts/benchmark-context.py,scripts/upgrade-target.py). - Updates Memory Bank schemas to schema v2 while keeping project history.
- Preserves custom domain rules in
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.
- 9d ago First seen · 63 lines · 70 tokens per session scan A 1b61148c1cad
project-upgrader is a skill published in the GitHub repository rumotion/ai-agent-project-template (1 stars, last pushed 19d ago), licensed MIT. It adds 70 tokens to every session and 872 once invoked, about $0.0003 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.
Other skills, from other repositories
saas-builder
Clone, verify, map, and build on top of ixartz/SaaS-Boilerplate for a user's SaaS idea. Use when a user wants to reuse SaaS Boilerplate, evaluate how their product fits it, or build product-specific pages, database schema, roles, permissions, MVP features, and launch scope on top of the boilerplate.
dashboard-builder
Build self-contained interactive HTML dashboards with charts, filters, and tables. Generates a single browser-openable file — no server or dependencies required.
bionic-decision-engine
Unified mathematical arbitrator for all resource allocation decisions — money, time, energy, relationships. Absorbs 46 decision protocols + 24 strategy protocols into one dense engine.
trading-risk-gate
Unified pre-trade safety gate: Ruin check (Law #1), ergodicity audit, and win-rate dominance validation. Absorbs: ergodicity-check, law-of-ruin, win-rate-dominance.
skill-creator-primer
You MUST load this skill before the skill-creator skill AND before making ANY change to, or conducting a review of ANY Agent Skill. Triggers include creating, editing, reviewing, or contributing to any part of an Agent Skill (description, frontmatter, body, references, scripts, trigger evals, conflicts, etc).
database-patterns
DB schema design and query tuning: normalization, indexing, N+1, transactions, EXPLAIN. Triggers: schema, index, slow query, N+1, PostgreSQL, MySQL, EXPLAIN, deadlock, query plan.