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/JairoTorregrosa/jaiskillsWrote 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/jairotorregrosa/jaiskills/deepen-plan)<a href="https://agentmods.dev/commands/jairotorregrosa/jaiskills/deepen-plan"><img src="https://agentmods.dev/badge/commands/jairotorregrosa/jaiskills/deepen-plan/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/jairotorregrosa/jaiskills/deepen-plan"><img src="https://agentmods.dev/badge/commands/jairotorregrosa/jaiskills/deepen-plan.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 | $0.00015 | $0.01025 |
| Opus 5 | $0.00008 | $0.00513 |
| Sonnet 5 | $0.00003 | $0.00205 |
| Haiku 4.5 | $0.00002 | $0.00103 |
Grade A, and why
deepen-plan 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 10d 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 — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Enhance a plan file with research insights by spawning parallel research agents.
Step 1: Locate the Plan File
If $ARGUMENTS specifies a path, use it. Otherwise, find the most recent *-plan.md file in the current working directory using Glob.
Read the plan file. If it cannot be found or read, report the error and stop.
Save the original content for later diffing.
Step 2: Parse Plan Structure
Parse the plan file to extract:
- Task sections: Each
### T<N>: <title>block with its description, location, acceptance criteria - Technologies: For each task, identify external technologies, frameworks, libraries, or APIs mentioned (e.g., "Python", "TypeScript", "React", "PostgreSQL", "Claude API")
- Internal references: File paths and internal patterns mentioned in each task
Build a list of (task_id, task_title, task_description, technologies[]) tuples.
Step 3: Optional Past Solutions Search
If docs/solutions/ exists in the project:
Spawn a jaiskills:insistir-learnings-researcher agent via the Task tool with a query summarizing the plan's overall goal and key technologies. This searches for relevant past solutions that could inform the plan.
This runs in parallel with Step 4.
Step 4: Spawn Parallel Researchers
For each task section that references at least one external technology, framework, or library:
Spawn a jaiskills:insistir-researcher agent via the Task tool. Each researcher receives:
- The task title and full description
- The specific technologies to research for that task
- The project's tech stack context (from package.json, tsconfig.json, etc.)
- Instruction to send findings back to you (the orchestrator) via SendMessage
Spawn all researchers in parallel — do NOT wait for one to finish before starting the next.
Skip tasks that only reference internal codebase patterns with no external dependencies.
Step 5: Collect All Findings
Wait for all spawned agents (researchers + optional learnings researcher) to send their findings via SendMessage.
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.
- 10d ago First seen · 119 lines · 15 tokens per session scan A caae7026ceb2
deepen-plan is a command published in the GitHub repository JairoTorregrosa/jaiskills (5 stars, last pushed 9d ago), licensed MIT. It adds 15 tokens to every session and 1,025 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
devkit.github.review-pr
Provides comprehensive GitHub pull request review with code quality, security, and best practices analysis. Use when reviewing a PR before merging.
t800-update
A command for updating the T-800 agent system from its GitHub repository. GitHub is a service for storing and versioning code.
lavra-work-ralph
Autonomous retry mode for bead work -- iterates until completion criteria are met or retry budget is exhausted.
t800-bootstrap
A first-run setup command for the T-800 plugin, intended for installation or a new user.
lavra-design
Orchestrate the full design pipeline -- brainstorm, plan, research, revise, review, lock.
pn-audit-security
OWASP-guided security review — auth posture, input validation, secrets, CORS, JWT, rate limiting. Surgical command for backend security. Use standalone or as part of pn-backend-audit.