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/boparaiamrit/skills-by-amritWrote 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/boparaiamrit/skills-by-amrit/research)<a href="https://agentmods.dev/commands/boparaiamrit/skills-by-amrit/research"><img src="https://agentmods.dev/badge/commands/boparaiamrit/skills-by-amrit/research/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/boparaiamrit/skills-by-amrit/research"><img src="https://agentmods.dev/badge/commands/boparaiamrit/skills-by-amrit/research.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 | $0.00796 |
| Opus 5 | $0.00010 | $0.00398 |
| Sonnet 5 | $0.00004 | $0.00159 |
| Haiku 4.5 | $0.00002 | $0.00080 |
Grade A, and why
research 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 11d 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 — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/research — Deep Research
Conduct thorough research on a topic before planning or implementation. Produces a structured research report.
Instructions
Step 1: Define Research Scope
From $ARGUMENTS, determine:
- Research question: What exactly are we investigating?
- Research type: Codebase analysis, technology evaluation, domain knowledge, or competitive analysis?
- Depth required: Quick scan (30 min) or deep dive (2+ hours)?
Step 2: Codebase Research (If Applicable)
For questions about the existing codebase:
# Find relevant files
grep -rn "[keyword]" --include="*.ts" --include="*.js" --include="*.py" . | grep -v node_modules | head -50
# Map structure of relevant area
find [directory] -type f -not -path '*/node_modules/*' | head -50
# Check git history for relevant changes
git log --all --oneline --grep="[keyword]" | head -20
# Find related tests
find . -path "*/test*" -name "*[keyword]*" -o -path "*/spec*" -name "*[keyword]*" | head -20
For each relevant file found:
- Read the full file — Don't skim. Understand the complete context.
- Trace imports/exports — Map the dependency chain.
- Read the tests — Tests document expected behavior.
- Check git blame — Who wrote it, when, and why?
Step 3: Technology Research (If Applicable)
For questions about technologies or approaches:
- Official documentation — Always start here
- GitHub examples — Look at how others use it
- Known issues — Check for gotchas, breaking changes, compatibility
- Alternatives — What else could solve this problem?
- Performance characteristics — Speed, memory, scalability
Step 4: Synthesize Findings
Create a structured research report. Save to .planning/research/[topic-slug].md:
# Research: [Topic]
## Question
[The specific research question]
## Executive Summary
[3-5 sentence summary of key findings]
## Key Findings
### Finding 1: [Title]
- **Source:** [file:line or URL]
- **Detail:** [What was discovered]
- **Implications:** [What this means for our work]
### Finding 2: [Title]
...
## Patterns & Conventions
- [Pattern 1]: [Description and where it's used]
- [Pattern 2]: ...
## Risks & Concerns
| Risk | Likelihood | Impact | Mitigation |
|------|-----------|--------|------------|
| [Risk] | Low/Med/High | Low/Med/High | [Action] |
## Recommendations
1. [Actionable recommendation]
2. [Actionable recommendation]
## References
- [Source 1] — [What it contributes]
- [Source 2] — [What it contributes]
## Open Questions
- [Question that needs further investigation]
- [Question that needs user input]
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.
- 11d ago First seen · 113 lines · 19 tokens per session scan A 36ad29613145
research is a command published in the GitHub repository boparaiamrit/skills-by-amrit (5 stars, last pushed 5mo ago), licensed MIT. It adds 19 tokens to every session and 796 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 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.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
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.