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-decisiongit 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-decision)<a href="https://agentmods.dev/skills/kastalien-research/thoughtbox/thoughtbox-decision"><img src="https://agentmods.dev/badge/skills/kastalien-research/thoughtbox/thoughtbox-decision.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 | $0.00045 | $0.01055 |
| Opus 5 | $0.00023 | $0.00528 |
| Sonnet 5 | $0.00009 | $0.00211 |
| Haiku 4.5 | $0.00005 | $0.00105 |
Grade A, and why
thoughtbox:decision 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 — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Use Thoughtbox branching to evaluate: $ARGUMENTS
Phase 1: Frame the Decision
- Create a session titled
Decision: [topic]. - Record thought 1: state the decision clearly.
- What are we choosing between?
- What constraints apply?
- What does success look like?
- Identify 2-4 distinct options (if not already provided by the user).
Phase 2: Branch and Explore
For each option, create a branch from thought 1 using branchFromThought
and branchId. Within each branch, gather evidence, assess pros/cons,
and identify risks using reasoning thoughts.
async () => {
await tb.thought({
thought: "Option A: PostgreSQL — ACID compliance, mature ecosystem, strong JSON support via jsonb",
thoughtType: "reasoning",
nextThoughtNeeded: true,
thoughtNumber: 2,
totalThoughts: 15,
branchFromThought: 1,
branchId: "postgresql"
});
}
Each branch should contain at minimum:
- Evidence: concrete facts supporting or undermining the option
- Pros/cons: structured assessment against the stated constraints
- Risks: what could go wrong, how recoverable is it
- Dependencies: what else changes if we pick this option
Use external tools (Grep, Read, web search) to gather real evidence rather than reasoning from memory alone.
Phase 3: Cross-Verify
Compare branches pairwise:
- Where do options agree? (shared strengths indicate low-risk ground)
- Where do they contradict? (genuine tradeoffs to weigh)
- Which criteria does each option win on?
- Are any options strictly dominated? (worse on every axis — eliminate)
Record cross-verification as a reasoning thought on the main trunk
(no branchId), referencing the branch thoughts by number.
See thoughtbox://guidance/parallel-verification for the parallel
exploration pattern.
Phase 4: Converge
Record a decision_frame thought with confidence and options. Exactly
one option must be selected: true.
async () => {
await tb.thought({
thought: "PostgreSQL wins: ACID required for financial data, jsonb handles semi-structured needs, team has existing expertise",
thoughtType: "decision_frame",
confidence: "high",
options: [
{ label: "PostgreSQL", selected: true, reason: "ACID + jsonb + team expertise" },
{ label: "MongoDB", selected: false, reason: "Better schema flexibility but ACID trade-off unacceptable" },
{ label: "DynamoDB", selected: false, reason: "Vendor lock-in, team unfamiliar" }
],
nextThoughtNeeded: false,
thoughtNumber: 15,
totalThoughts: 15
});
}
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 · 130 lines · 45 tokens per session scan A 3ff2c2d6dfcf
thoughtbox:decision is a skill published in the GitHub repository Kastalien-Research/thoughtbox (64 stars, last pushed 1mo ago), licensed MIT. It adds 45 tokens to every session and 1,055 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
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.