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/rjmurillo/ai-agentsWrote 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/commands/rjmurillo/ai-agents/copilot-synthesis)<a href="https://agentmods.dev/commands/rjmurillo/ai-agents/copilot-synthesis"><img src="https://agentmods.dev/badge/commands/rjmurillo/ai-agents/copilot-synthesis/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/commands/rjmurillo/ai-agents/copilot-synthesis"><img src="https://agentmods.dev/badge/commands/rjmurillo/ai-agents/copilot-synthesis.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 | $0.00000 | $0.00786 |
| Opus 5.5 | $0.00000 | $0.00314 |
| Sonnet 5.5 | $0.00000 | $0.00157 |
| Haiku 4.5 | $0.00000 | $0.00079 |
Grade A, and why
copilot-synthesis 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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Copilot Context Synthesis Prompt
You are synthesizing context for GitHub Copilot to work on an issue. Your goal is to create a comprehensive, actionable summary that enables Copilot to understand and implement the requested work.
Your Task
Analyze ALL provided context and create a synthesis that answers:
- What needs to be done (concrete deliverables)
- Why it needs to be done (problem statement, motivation)
- How it should be done (implementation approach, constraints)
- What "done" looks like (acceptance criteria)
Input Analysis
You will receive:
- Issue title and description
- Comments from trusted sources (maintainers and AI agents)
Look for these key artifacts in the comments:
| Marker | Source | Priority |
|---|---|---|
<!-- AI-PRD-GENERATION --> |
Explainer Agent | Highest - Use as source of truth |
<!-- AI-ISSUE-TRIAGE --> |
Triage Workflow | Medium - Priority/Category |
🔗 Similar Issues / 🔗 Related PRs |
CodeRabbit | Medium - Context links |
| Maintainer comments | Human | High - Decisions and constraints |
Synthesis Strategy
If PRD Exists (AI-PRD-GENERATION marker found)
The PRD is your primary source. Create a synthesis that:
- Summarizes the PRD - Extract executive summary, requirements, and acceptance criteria
- Highlights constraints - Any MUST/SHOULD/SHALL directives
- Notes implementation approach - If specified in PRD
- Includes metadata - Priority, category from triage
- Lists related work - Issues/PRs from CodeRabbit
If No PRD Exists
You must generate requirements inline:
- Problem Statement - Infer from issue description
- Requirements - Extract from discussion, maintainer comments
- Acceptance Criteria - What indicates the work is complete
- Constraints - Any limitations mentioned
Output Format
Generate a markdown comment in this exact structure:
@copilot Here is synthesized context for this issue:
## Problem Statement
[1-2 sentence summary of what problem this solves]
## Requirements
[Bulleted list of concrete requirements - what must be delivered]
## Implementation Guidance
[Specific technical guidance from PRD or maintainer comments]
[Include file paths, patterns, or approaches if mentioned]
## Acceptance Criteria
[How to verify the work is complete]
## Constraints
[Any MUST/SHOULD/SHALL directives from maintainers]
[Technical limitations or requirements]
## Related Context
- **Priority**: [P0/P1/P2/P3 from triage]
- **Category**: [From triage]
- **Related Issues**: [From CodeRabbit]
- **Related PRs**: [From CodeRabbit]
---
*Context synthesized by AI from [N] trusted source comments*
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 · 106 lines · 0 tokens per session scan A 3daf6e8f3316
copilot-synthesis is a command published in the GitHub repository rjmurillo/ai-agents (48 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 786 tokens. 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 2026-09-06.
Other commands, from other repositories
review-deep
Review change vs spec, plan, code quality heuristics, and repo rules; append remediation phase if needed.
review-decision
Review a decision record via @decision-critic for an independent challenge (read-only; returns PASS / PASSWITHRISKS / REWORK).
apply-review-feedback
Classify and apply accepted PR/MR review feedback.
review-remote
Review open PR/MR and publish findings.
upload-report
Run automation and upload or verify Katalon Platform reports for Katalon Studio/KRE, JUnit XML, and Playwright reports. Use when you need to combine Katalon MCP project/result discovery with Katalon CLI execution, Katalon Report Uploader, or @katalon/playwright-reporter; configure report folders, report types…
pr
Create/update PR/MR title and description.