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 synthesizegit 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/synthesize)<a href="https://agentmods.dev/skills/kastalien-research/thoughtbox/synthesize"><img src="https://agentmods.dev/badge/skills/kastalien-research/thoughtbox/synthesize.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 | $0.00034 | $0.00518 |
| Opus 5 | $0.00017 | $0.00259 |
| Sonnet 5 | $0.00007 | $0.00104 |
| Haiku 4.5 | $0.00003 | $0.00052 |
Grade A, and why
synthesize 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.
What it actually says
Synthesize knowledge on this topic: $ARGUMENTS
Process
1. Source Inventory
Identify relevant knowledge sources across these categories:
| Source Type | Where to Look |
|---|---|
| Code | Current codebase (Glob/Grep), implementation patterns, tests, comments |
| Documentation | Specs, READMEs, ADRs, API docs in the repo |
| Memory | .Codex/ project memory, agent memory, previous learnings |
| External research | WebSearch, Exa for papers, blog posts, community discussion |
| Issue history | selected tracker or handoff entries, closed issues, decision rationale |
Scan at least 3 source types. Don't rely on a single category.
2. Extract & Classify
For each source, extract:
- Claims — specific assertions about the topic
- Patterns — recurring approaches or structures
- Conflicts — where sources disagree
- Gaps — what no source addresses
3. Integration
Three integration strategies, used as appropriate:
Convergent — Multiple sources agree. High confidence. Extract the common principle.
Divergent — Sources disagree. Analyze why (different contexts? different values? different data?). Don't force resolution — document the conditions under which each view applies.
Complementary — Sources cover different facets. Weave into a complete picture, noting which source contributed which piece.
4. Output
## Synthesis: [Topic]
### Sources Consulted
- [Source type]: [what was found]
### Convergent Findings (high confidence)
- [Finding]: supported by [sources]
### Divergent Findings (context-dependent)
- [Claim A] (applies when [X]) vs. [Claim B] (applies when [Y])
### Gaps
- [What no source addressed]
### Integrated Understanding
[Coherent narrative combining all sources — the actual synthesis]
### Confidence Assessment
[Overall confidence and what would increase it]
### Actionable Next Steps
[What to do with this understanding]
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 · 71 lines · 34 tokens per session scan A dceb613cfc51
synthesize is a skill published in the GitHub repository Kastalien-Research/thoughtbox (64 stars, last pushed 1mo ago), licensed MIT. It adds 34 tokens to every session and 518 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.