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 commands/hoja-solutions/agent-stdlib/researchgit clone --depth 1 https://github.com/Hoja-Solutions/agent-stdlibWhat 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 | $0.00030 | $0.00364 |
| Opus 5 | $0.00015 | $0.00182 |
| Sonnet 5 | $0.00006 | $0.00073 |
| Haiku 4.5 | $0.00003 | $0.00036 |
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 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.
What it actually says
You are the lead agent in an orchestrator-worker research run. Follow the
multi-agent-orchestration skill in this pack. The question:
$ARGUMENTS
Work in these steps:
-
Decide the shape. If the question is narrow or single-source, answer it directly and stop. Multi-agent costs roughly 15x the tokens of one agent and only pays off for breadth-first work. Use the rest of this flow only when the question splits into independent parts worth exploring in parallel.
-
Decompose. Break the question into 3 to 5 sub-questions that do not overlap. Scale the count to complexity: simple gets fewer, complex gets more.
-
Set up shared notes. Create a
research-notes/directory. Each worker writes to its own file there, so findings do not funnel through your context and get lost at the bottleneck. -
Dispatch workers in parallel. In a single message, spawn one
research-workersubagent per sub-question (multiple Task calls at once). Give each: its objective, the notes file to write, and explicit boundaries so it stays out of the others' scope. -
Synthesize. Read the workers' note files, resolve contradictions, and write one answer that cites sources. Judge the final synthesis, not the path each worker took.
If a worker fails, note the gap in the synthesis rather than silently dropping its sub-question.
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 · 36 lines · 30 tokens per session scan A a2d56e280ab8
research is a command published in the GitHub repository Hoja-Solutions/agent-stdlib (1 stars, last pushed 1mo ago), licensed MIT. It adds 30 tokens to every session and 364 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 2026-08-31.
Other commands, from other repositories
README
Git workflow and quality assurance commands for the claude-skills repository.
research-perplexity
Run a deep research query using Perplexity's /research mode via Playwright browser automation. This is an alternative to /export-to-council that uses Perplexity's dedicated research mode instead of multi-model council.
dispatcher
Pick the next-best repo to work on across the portfolio — rank free repos, recommend one, claim its lease atomically, and route to the entry command.
tldr
Re-apply TLDR rules for this turn (verdict first, no filler).
execute
Interactive workflow for workspace isolation, pane-delegated implementation, testing, review, and cleanup.
me-figure-discussion
Write or review thermal-fluid figure discussion with observation, physical mechanism, comparison, uncertainty, and claim limits.