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 source-of-truth-preflightgit 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/source-of-truth-preflight)<a href="https://agentmods.dev/skills/kastalien-research/thoughtbox/source-of-truth-preflight"><img src="https://agentmods.dev/badge/skills/kastalien-research/thoughtbox/source-of-truth-preflight/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/kastalien-research/thoughtbox/source-of-truth-preflight"><img src="https://agentmods.dev/badge/skills/kastalien-research/thoughtbox/source-of-truth-preflight.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00058 | $0.00975 |
| Opus 5 | $0.00029 | $0.00487 |
| Sonnet 5 | $0.00012 | $0.00195 |
| Haiku 4.5 | $0.00006 | $0.00097 |
Grade A, and why
source-of-truth-preflight 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 — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Source Of Truth Preflight
Run this skill before editing code for non-trivial feature work, especially when the task touches domain models, state machines, runtime providers, repository contracts, schema migrations, or existing subsystem boundaries.
This is a short gate, not a design ceremony. Produce the report before coding. If the report cannot identify the canonical model or enforcement points, pause instead of implementing.
Trigger Conditions
Use this skill when any of these are true:
- adding or changing lifecycle states
- compiling, parsing, importing, exporting, or graduating a domain object
- adding a repository method, migration, runtime provider, broker, or handler
- introducing a new type whose name overlaps an existing concept
- seeing two or more files define similar domain terms
- after two surprises during a task
Preflight Steps
1. Identify The Unit
State the requested unit in one sentence. Name explicit non-goals.
2. Inventory Existing Models
Search before designing. Prefer rg:
rg -n "export (interface|type|class|const) .*<Concept>|<Concept>Schema|type <Concept>|interface <Concept>" src apps .specs .adr docs
rg -n "from ['\"].*<concept>.*['\"]|<Concept>" src apps
Record:
- canonical model candidates with file references
- legacy or competing models with file references
- runtime/schema/repository boundaries that already enforce the concept
3. Choose The Canonical Source Of Truth
Name the model the implementation will build on. If there are multiple live models, classify each as one of:
canonical: new work should build herelegacy-live: still used, but not the right extension pointadapter-only: used only to translate between systemscontrol-plane: metadata/registry state, not the domain object itselftest-fixture: fixture-only, not production semantics
If the choice is not obvious, pause and ask for a decision.
4. Illegal-State Pass
List the states that should be impossible. Check whether current types make them impossible.
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 · 158 lines · 58 tokens per session scan A 3b1da52f473c
source-of-truth-preflight is a skill published in the GitHub repository Kastalien-Research/thoughtbox (64 stars, last pushed 1mo ago), licensed MIT. It adds 58 tokens to every session and 975 once invoked, about $0.0003 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 2026-09-03.
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.
CSOC Operations & Playbook Automation
SOC alert triage, incident playbook automation, escalation workflows, shift reporting, and SOC KPI tracking.