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/Jamie-BitFlight/claude_skillsnpx agentmods add commands/jamie-bitflight/claude_skills/process-research-integrationWrote 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/jamie-bitflight/claude_skills/process-research-integration)<a href="https://agentmods.dev/commands/jamie-bitflight/claude_skills/process-research-integration"><img src="https://agentmods.dev/badge/commands/jamie-bitflight/claude_skills/process-research-integration.svg" alt="Measured on agentmods" 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 | $0.00032 | $0.00846 |
| Opus 5 | $0.00016 | $0.00423 |
| Sonnet 5 | $0.00006 | $0.00169 |
| Haiku 4.5 | $0.00003 | $0.00085 |
Grade A, and why
process-research-integration 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 8d 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 — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Process Research Integration Opportunities
Batch process all research markdown files to discover and document integration opportunities with existing repository capabilities.
What This Does
- Finds all markdown files in
research/(excluding README.md files) - For each research file, spawns the research-context-agent
- Agent reads the file, searches for connections, appends Integration Opportunities section
- Reports summary of all processed files
Usage
/process-research-integration
Options:
# Process a specific category
/process-research-integration --category developer-tools
# Process a single file
/process-research-integration --file research/developer-tools/loguru.md
# Force reprocess (replace existing Integration Opportunities)
/process-research-integration --force
# Dry run (show what would be processed without making changes)
/process-research-integration --dry-run
Implementation
This command uses the batch processing script at ./scripts/process-research-integration.py.
Script Features:
- Cross-platform Python script using
uvwith inline script metadata - CLI built with Typer for command-line options
- Rich console output for progress tracking and results visualization
- Supports category filtering, single file processing, force reprocessing, and dry-run mode
For manual invocation:
# Using uv (recommended - handles dependencies automatically)
uv run ./scripts/process-research-integration.py --help
# Or make executable and run directly
chmod +x ./scripts/process-research-integration.py
./scripts/process-research-integration.py --help
Processing workflow:
- Find research files matching criteria (category/file/all)
- For each file, spawn research-context-agent via Agent tool
- Agent reads, analyzes, validates with WebSearch, appends Integration Opportunities
- Track and display results in formatted tables
Agent orchestration (to be implemented):
- Use Agent tool to spawn research-context-agent instances
- Pass file path as parameter
- Sequential processing (one file at a time)
- Collect results and generate summary
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.
- 8d ago First seen · 139 lines · 32 tokens per session scan A d965c1aa8ef2
process-research-integration is a command published in the GitHub repository Jamie-BitFlight/claude_skills (66 stars, last pushed today), licensed MIT. It adds 32 tokens to every session and 846 once invoked, about $0.0002 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 2026-08-30.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.