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.
git clone --depth 1 https://github.com/ils15/pantheon-legacyWrote 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/agents/ils15/pantheon-legacy/auto-continue-template)<a href="https://agentmods.dev/agents/ils15/pantheon-legacy/auto-continue-template"><img src="https://agentmods.dev/badge/agents/ils15/pantheon-legacy/auto-continue-template/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/agents/ils15/pantheon-legacy/auto-continue-template"><img src="https://agentmods.dev/badge/agents/ils15/pantheon-legacy/auto-continue-template.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 | $0.00019 | $0.00778 |
| Opus 5.5 | $0.00008 | $0.00311 |
| Sonnet 5.5 | $0.00004 | $0.00156 |
| Haiku 4.5 | $0.00002 | $0.00078 |
Grade A, and why
auto-continue-template 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 1mo 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 — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
⚡ Auto-Continue Template
Embed this section into any agent YAML file to enable disciplined automatic continuation through multi-step tasks, while preserving mandatory safety gates.
Core Principle
Auto-continue through unambiguous work. Stop only at real decision points.
When Auto-Continue Is Active
- ✅ Multi-step tasks with clear sequential steps
- ✅ TDD cycles (RED→GREEN→REFACTOR)
- ✅ Batch operations on multiple files
- ❌ After Themis review (stop for approval)
- ❌ After unexpected errors
- ❌ Before destructive operations
- ❌ When requirements are ambiguous
Auto-Continue Protocol
- Create todos for all steps at start
- Mark first todo in_progress
- Complete work → mark completed immediately
- Mark next todo in_progress without asking
- Stop at safety gates (Themis review, errors, human approval)
- After gate approval, resume with next todo
Never batch-complete todos. Mark each completed as soon as done.
Session Heartbeat
- Every 5 turns, call
pantheon-code-mode execute_code_script checkpoint_session.py save <slug> - Saves checkpoint-N.json with current state
- Updates heartbeat.json timestamp
- If interrupted, use
pantheon://deepwork/<slug>/checkpoint-N.jsonto resume
Idle Detection
- No tool call for 60s → log heartbeat warning
- No tool call for 120s → trigger anti-stall
- No tool call for 300s → auto-checkpoint and pause
Progress Reporting
- Every 5 turns: update STATUS.md with current phase, completed, and pending
- Use markdown checklist format
- Flag blockers immediately
Safety Checks Before Continuing
- Previous step completed successfully (tests pass, no errors)
- Next step is within approved plan scope
- No new blocking issues emerged
- Steps counter has sufficient budget remaining
Cooldown Pattern
Phase Summary Template
Phase N complete. Summary:
- What was done: <2 bullet points>
- What changed: <files modified>
- What's next: <Gate 2 review OR next phase>
- Will continue: <YES / after gate approval>
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.
- 1mo ago First seen · 103 lines · 19 tokens per session scan A e556b3ae5354
auto-continue-template is an agent published in the GitHub repository ils15/pantheon-legacy (12 stars, last pushed 26d ago), licensed MIT. It adds 19 tokens to every session and 778 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-09-03.
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.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
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.
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.
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.