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 skills/kastalien-research/thoughtbox/research-tasknpx skills add Kastalien-Research/thoughtbox --skill research-taskgit clone --depth 1 https://github.com/Kastalien-Research/thoughtboxWrote 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/skills/kastalien-research/thoughtbox/research-task)<a href="https://agentmods.dev/skills/kastalien-research/thoughtbox/research-task"><img src="https://agentmods.dev/badge/skills/kastalien-research/thoughtbox/research-task.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 | $0.00039 | $0.01403 |
| Opus 5 | $0.00019 | $0.00701 |
| Sonnet 5 | $0.00008 | $0.00281 |
| Haiku 4.5 | $0.00004 | $0.00140 |
Grade A, and why
research-task 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 4d 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 — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Research this topic: $ARGUMENTS
Workflow
Phase 1: Task Characterization
Rate the research task on each dimension (1-5):
| Dimension | 1 (Low) | 5 (High) |
|---|---|---|
| Scope | Point question (single fact) | Frontier mapping (state of entire field) |
| Domain structure | Single field, established methods | Distant cross-domain analogy |
| Evidence type | Empirical data, measurements | Theoretical arguments, first-principles |
| Time horizon | What's true right now | What could become true (speculative) |
| Fidelity | Ballpark / directional | Rigorous / publication-grade |
Phase 1b: Workflow Library Query
Query the MAP-Elites workflow library for strategies matching this task's coordinates:
sqlite3 research-workflows/workflows.db "SELECT id, name, archetype, fitness_score FROM workflows WHERE status IN ('active', 'seed') ORDER BY fitness_score DESC LIMIT 10;"
For more targeted retrieval, filter by behavioral region:
sqlite3 research-workflows/workflows.db "SELECT w.id, w.name, ws.name as step_name, ws.description, ws.rationale FROM workflows w JOIN workflow_steps ws ON w.id = ws.workflow_id WHERE w.archetype = '<archetype>' AND w.status IN ('active', 'seed') ORDER BY w.fitness_score DESC, ws.step_order;"
Use retrieved workflows to inform Phase 2 strategy selection. Prefer workflows with high fitness scores and usage counts.
Phase 2: Strategy Selection
Based on the characterization and library query, select the most appropriate research archetype:
Exploratory (high scope, moderate fidelity)
- Quick landscape scan — 15-minute overview of a new area
- Deep literature review — comprehensive survey of a mature field
- Trend detection — what's gaining momentum
- White space identification — what isn't being worked on that should be
Confirmatory (low scope, high fidelity)
- Fact-checking pipeline — verify specific claims with primary sources
- Consensus mapping — what do experts agree/disagree on
- Replication check — has this finding held up under scrutiny
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.
- 4d ago First seen · 138 lines · 39 tokens per session scan A 6e8133574e8d
research-task is a skill published in the GitHub repository Kastalien-Research/thoughtbox (64 stars, last pushed 1mo ago), licensed MIT. It adds 39 tokens to every session and 1,403 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 skills, from other repositories
unity-addressables
Manage Addressables groups, entries, profiles and content builds (com.unity.addressables, reflection-based).
impeccable
Use when the user wants to design, redesign, shape, critique, audit, polish, clarify, distill, harden, optimize, adapt, animate, colorize, extract, or otherwise improve a frontend interface. Covers websites, landing pages, dashboards, product UI, app shells, components, forms, settings, onboarding, and empty states.…
render-airdrop-carousel
Assemble a viral iOS "AirDrop" notification-carousel video ad (≈6–8s, 9:16) from a brand line plus 6–16 real product photos — a native AirDrop share-sheet card ("Brand would like to share a · Decline / Accept") springs up and its preview window CYCLES through the products, landing on a range/lineup payoff with an…
render-3d-product-showcase
Assemble a premium 3D product-showcase ad from a config — four beat clips (an orbiting hero rotation, a macro push-in, a physics reveal, a typographic close) normalized to the brand-color canvas, hard-concatenated in order, closed on a deterministic Playwright brand end card, and mixed under one instrumental bed at…
opik-diagnose
Surface the Opik traces worth a developer's attention, ranked by signal — errors, failed tool calls, latency, regressions, and low online-eval scores — plus Diagnostics issues. Reads live/production traces via the SDK (searchtraces and agentinsights) and works with no MCP; uses the MCP issue entity when connected.…
Threat Hunting & IOC Analysis
IOC extraction, threat intelligence correlation, MITRE ATT&CK mapping, hunt hypothesis generation, and detection rule creation.