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 skills add Kastalien-Research/thoughtbox --skill thoughtbox-teamgit 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/thoughtbox-team)<a href="https://agentmods.dev/skills/kastalien-research/thoughtbox/thoughtbox-team"><img src="https://agentmods.dev/badge/skills/kastalien-research/thoughtbox/thoughtbox-team.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00096 | $0.00656 |
| Opus 5 | $0.00048 | $0.00328 |
| Sonnet 5 | $0.00019 | $0.00131 |
| Haiku 4.5 | $0.00010 | $0.00066 |
Grade A, and why
thoughtbox-team 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Thoughtbox Team
Spawn a 2-agent team: you (lead) + a background analyst teammate that monitors your Thoughtbox session.
When to Use
Use this when you're about to do significant Thoughtbox reasoning — sessions where you'll record 10+ thoughts and want background analysis of contradictions, evolution candidates, and session digests without having to orchestrate it yourself.
Don't use this for quick 1-3 thought sessions — the coordination overhead isn't worth it.
How to Spawn
Tell Codex you want to create a team. The analyst teammate should be configured with:
- Name:
analyst - Role: Read the agent definition at
.Codex/agents/thoughtbox-analyst.mdand use it as the teammate's instructions - Model: Haiku (cost-efficient for background monitoring)
- Focus: Monitor the Thoughtbox session specified by $ARGUMENTS, or the most recent active session
Example spawn prompt:
Create an agent team with one teammate:
- Name: analyst
- Instructions: [contents of .Codex/agents/thoughtbox-analyst.md]
- Task: Monitor Thoughtbox session [SESSION_ID] for evolution candidates and contradictions. Message me when you find thoughts that should be revised. Generate a digest every 20 thoughts.
Working with the Analyst
Once the team is running:
- Do your work normally. Record thoughts via
thoughtbox_executeas usual. - Watch for messages. The analyst will message you when it finds evolution candidates.
- Respond to evolution signals. When the analyst says "Thought 55 may contradict thoughts 5, 24", you decide whether to revise.
- Request digests. Message the analyst: "Give me a digest of where we are."
What the Analyst Does
- Periodically checks the session for new thoughts
- Runs deterministic evolution candidate detection (word overlap, structural heuristics)
- Flags
assumption_updateanddecision_framethoughts for special attention - Generates compressed digests at milestones (~every 20 thoughts)
- Messages you with concise, actionable findings
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 · 63 lines · 96 tokens per session scan A e19bbac824fe
thoughtbox-team is a skill published in the GitHub repository Kastalien-Research/thoughtbox (64 stars, last pushed 1mo ago), licensed MIT. It adds 96 tokens to every session and 656 once invoked, about $0.0005 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
matlab
Build, review, migrate, and safely plan MATLAB or GNU Octave numerical workflows, including arrays, tabular/time data, tests, projects, graphics, MAT files, and explicit Python interoperability.
phylogenetics
Build and analyze phylogenetic trees using MAFFT (multiple alignment), IQ-TREE 2 (maximum likelihood), and FastTree (fast NJ/ML). Visualize with ETE3 or FigTree. For evolutionary analysis, microbial genomics, viral phylodynamics, protein family analysis, and molecular clock studies.
data-charts-tako
Search and visualize the world's data - get charts, insights, and embeddable knowledge cards for finance, economics, demographics, sports, and more.
unity-addressables
Manage Addressables groups, entries, profiles and content builds (com.unity.addressables, reflection-based).
unity-yaml-editing
Last-resort guidance for safely hand-editing Unity YAML.
Threat Hunting & IOC Analysis
IOC extraction, threat intelligence correlation, MITRE ATT&CK mapping, hunt hypothesis generation, and detection rule creation.