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-refactorgit 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-refactor)<a href="https://agentmods.dev/skills/kastalien-research/thoughtbox/thoughtbox-refactor"><img src="https://agentmods.dev/badge/skills/kastalien-research/thoughtbox/thoughtbox-refactor/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/thoughtbox-refactor"><img src="https://agentmods.dev/badge/skills/kastalien-research/thoughtbox/thoughtbox-refactor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
SkillSpector: 1 finding, up to low
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- low Excessive Agency · line 69 Skill's behavior or capabilities extend beyond its stated purpose. Scope creep allows an agent to perform actions unrelated to its documented functionality, increasing the attack surface.Fix: Limit the skill's scope to its documented purpose. Remove instructions that enable the agent to perform actions outside its stated functionality.
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 | $0.00111 | $0.01016 |
| Opus 5.5 | $0.00044 | $0.00406 |
| Sonnet 5.5 | $0.00022 | $0.00203 |
| Haiku 4.5 | $0.00011 | $0.00102 |
Grade A, and why
thoughtbox:refactor 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 1mo 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 — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Theseus Refactoring Protocol
Refactoring has a failure mode: scope creep. You start renaming one function and end up restructuring three modules. Theseus prevents this by locking your file scope upfront, requiring explicit justification to expand it, and tracking how often your changes break tests.
Core Mechanics
- Scope: declared file list at init — you can only touch these files
- Visa: explicit request to touch an out-of-scope file (requires justification)
- Checkpoint: submit each logical change for audit before proceeding
- B-counter: tracks test failures — high B means your refactor is causing breakage
- Terminal state: completed, abandoned, or rolled back
Workflow
Phase 1: Declare Scope
Identify every file you expect to touch. Be specific — this is your contract.
// thoughtbox_execute
async () => {
return await tb.theseus({
operation: "init",
scope: ["src/auth/handler.ts", "src/auth/types.ts", "src/auth/middleware.ts"],
description: "Extract token validation into standalone module"
});
}
The session starts with B=0 (no test failures yet).
Phase 2: Work Within Scope
Make changes to declared files. After each logical unit of work:
- Checkpoint the change:
async () => {
return await tb.theseus({
operation: "checkpoint",
diffHash: "abc123", // git diff hash or commit SHA
commitMessage: "refactor(auth): extract TokenValidator class",
approved: true,
feedback: "Clean extraction, no behavior change"
});
}
- Run tests and record outcome:
async () => {
return await tb.theseus({
operation: "outcome",
testsPassed: true,
details: "All 47 auth tests pass"
});
}
If tests fail, B increments. If B reaches 3, stop and reassess — your refactor is causing too much breakage.
Phase 3: Expand Scope (If Needed)
If you discover you need to touch a file outside your declared scope, request a visa:
async () => {
return await tb.theseus({
operation: "visa",
filePath: "src/routes/login.ts",
justification: "Login route imports TokenValidator directly — need to update import path",
antiPatternAcknowledged: true
});
}
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.
- 1mo ago First seen · 127 lines · 111 tokens per session scan A 422615e8a222
thoughtbox:refactor is a skill published in the GitHub repository Kastalien-Research/thoughtbox (65 stars, last pushed 3mo ago), licensed MIT. It adds 111 tokens to every session and 1,016 once invoked, about $0.0004 per session on Opus 5.5. 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
Builds, reviews, migrates, and plans MATLAB or GNU Octave numerical workflows. Use for arrays, tabular/time data, tests, projects, graphics, MAT files, and explicit Python interoperability.
phylogenetics
Builds and analyzes phylogenetic trees using MAFFT multiple sequence alignment, IQ-TREE maximum likelihood with ModelFinder and branch support, and FastTree approximate inference. Uses ETE3 for tree summaries and visualization. Applies to homologous nucleotide or protein sequences, microbial gene trees, protein…
unity-yaml-editing
Last-resort guidance for safely hand-editing Unity YAML.
ad-policy-check
Checks paid ads against the ad platform's rules (Meta, TikTok, Google, LinkedIn and others) and the brand's category rules: the copy, on-image or on-screen text, pictures and people. Rewrites what can be fixed honestly, adds the disclosures that are needed, and flags anything that needs a human or legal review, with…
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 chosen backdrop colour, hard-concatenated in order, closed on a deterministic Playwright brand end card, and mixed under one instrumental bed…
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…