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/atebites-hub/pjtemplate/upgradegit clone --depth 1 https://github.com/atebites-hub/PJTemplateWhat 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 | $0.02033 |
| Opus 5 | $0.00000 | $0.01017 |
| Sonnet 5 | $0.00000 | $0.00407 |
| Haiku 4.5 | $0.00000 | $0.00203 |
Grade A, and why
upgrade scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
TOKEN="$(curl -s "https://ghcr.io/token?scope=repository:aquasecurity/trivy:pull" \ How it starts
The opening of the file, as written. The whole thing — 191 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Upgrade & Maintenance Guide
Purpose. How to refresh this template's pinned artifacts (deps, actions, scanner images, the ODW and J-Space submodules) and how a project derived from this template pulls in upstream template fixes. This is a process doc, not one of the 10 core documents.
One rule above all: everything is pinned (Python deps by hash, GitHub Actions by commit SHA, scanner containers by image digest, OpenGrep by SHA-256, ODW and J-Space by submodule commit). An upgrade is a deliberate, reviewed pin rotation — never a floating reference.
1. Python dependencies
Lockfiles (requirements.txt, requirements-dev.txt, requirements-notebooks.txt)
are compiled from the .in sources with hashes. Never edit a .txt
directly; bump the .in and re-compile.
# Edit the source pins (e.g. bump a floor, add a dep) in requirements*.in,
# then regenerate every lockfile WITH hashes from a clean Python 3.12 env:
pip-compile --generate-hashes --allow-unsafe --resolver=backtracking \
requirements.in -o requirements.txt
pip-compile --generate-hashes --allow-unsafe --resolver=backtracking \
requirements-dev.in -o requirements-dev.txt
pip-compile --generate-hashes --allow-unsafe --resolver=backtracking \
requirements-notebooks.in -o requirements-notebooks.txt
The [tool.pip-tools] block in pyproject.toml already sets those flags, so a
bare pip-compile requirements.in honors them. Track CVE floors with comments
in the .in files (e.g. # CVE-2026-XXXX fixed in >=X.Y.Z).
Verify before committing:
python -m pip install --require-hashes -r requirements-dev.txt && python -m pip check
./scripts/security/supply-chain-audit.sh # pip-audit + OSV-Scanner over BOTH lockfiles
Dependabot does NOT do this.
.github/dependabot.ymlexcludes thepipecosystem on purpose — Dependabot mutates the compiled.txtdirectly and fights--require-hashes. Python bumps are always the manual.in→pip-compileflow above.
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.
- 2d ago First seen · 191 lines · 0 tokens per session scan A bec8ee40bad7
upgrade is an agent published in the GitHub repository atebites-hub/PJTemplate (2 stars, last pushed 10d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,033 tokens. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
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.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.