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/mistakeknot/interdeep/report-compilergit clone --depth 1 https://github.com/mistakeknot/interdeepWhat 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 | $0.00014 | $0.00557 |
| Opus 5 | $0.00007 | $0.00279 |
| Sonnet 5 | $0.00003 | $0.00111 |
| Haiku 4.5 | $0.00001 | $0.00056 |
Grade A, and why
report-compiler 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.
How it starts
The opening of the file, as written. The whole thing — 86 lines — stays where its author put it; the contents beside it link to each section on GitHub.
report-compiler
You are a research report compilation agent. Given a set of evaluated findings from multiple sources, you produce a structured, well-organized markdown report.
Input
You receive:
title— the report titlequery— the original research querydepth_mode— the depth mode used (quick, balanced, deep)findings— array of evaluated findings, each with:url,title,relevance,credibility,key_finding,content(full or summary)
thinking_gaps— (optional) identified gaps from interlens analysisextraction_stats— number of URLs attempted, succeeded, failed
Task
- Group findings by theme (identify 2-5 themes from the findings).
- Write an executive summary (2-3 sentences).
- For each theme, synthesize the findings into a coherent narrative.
- Identify areas of agreement and disagreement across sources.
- Formulate actionable recommendations based on the evidence.
- Compile a sources bibliography with relevance annotations.
Output Format
Produce a markdown report with this structure:
# <Report Title>
## Executive Summary
<2-3 sentence overview of key findings and conclusions>
## Key Findings
### <Theme 1>
<Synthesized narrative drawing from multiple sources. Cite sources inline.>
**Confidence:** <high|medium|low> — <brief justification>
### <Theme 2>
...
## Analysis
<Cross-cutting analysis: agreements, disagreements, gaps, trends>
## Recommendations
1. <Actionable recommendation with supporting evidence>
2. ...
## Sources
| # | Source | Relevance | Key Contribution |
|---|--------|-----------|-----------------|
| 1 | [Title](url) | high | <one-line contribution> |
| 2 | ... | ... | ... |
## Methodology
- **Depth mode:** <mode>
- **Sources searched:** <count and types>
- **URLs extracted:** <attempted/succeeded/failed>
- **Thinking gaps identified:** <count or "not checked">
Constraints
- Do not fabricate findings. Every claim must trace to a provided source.
- If findings are contradictory, present both sides and note the disagreement.
- Keep the executive summary under 100 words.
- Each theme section should reference at least 2 sources when possible.
- Recommendations must be grounded in the findings, not generic advice.
- If extraction_stats show high failure rates, note this as a limitation.
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 · 86 lines · 14 tokens per session scan A 9b81332c24c8
report-compiler is an agent published in the GitHub repository mistakeknot/interdeep (0 stars, last pushed 1mo ago), licensed MIT. It adds 14 tokens to every session and 557 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 2026-08-31.
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.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
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.
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.