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 implementgit 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/implement)<a href="https://agentmods.dev/skills/kastalien-research/thoughtbox/implement"><img src="https://agentmods.dev/badge/skills/kastalien-research/thoughtbox/implement/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/implement"><img src="https://agentmods.dev/badge/skills/kastalien-research/thoughtbox/implement.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 | $0.00034 | $0.00425 |
| Opus 5.5 | $0.00014 | $0.00170 |
| Sonnet 5.5 | $0.00007 | $0.00085 |
| Haiku 4.5 | $0.00003 | $0.00042 |
Grade A, and why
implement 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.
What it actually says
Implement the following specification: $ARGUMENTS
Workflow
Phase 1: Requirement Extraction (10% of effort)
- Read the spec file (if a path was given) or parse the description
- Extract atomic, testable requirements
- Identify dependencies (internal and external)
- Create a checklist of acceptance criteria
Phase 2: Test-First Development (25% of effort)
For each requirement:
- Write a failing test that captures the requirement
- Run the test to confirm it fails (red)
- Move to the next requirement
Phase 3: Implementation (50% of effort)
For each failing test (in dependency order):
- Implement the minimum code to make the test pass
- Run the test to confirm it passes (green)
- Refactor if needed (keeping tests green)
- Check for regressions after each change
Spiral detection: If you find yourself editing the same files 3+ times without making progress, stop and reassess your approach.
Phase 4: Verification (15% of effort)
- Run the full test suite
- Walk through each acceptance criterion — does the implementation satisfy it?
- Check for edge cases not covered by tests
- Report results
Output
At completion, present:
## Implementation Summary
Requirements: [N total, N implemented, N deferred]
Tests: [N passing, N failing, N skipped]
Files changed: [list]
Acceptance Criteria:
- [criterion 1]: PASS | FAIL
- [criterion 2]: PASS | FAIL
Deferred items (if any):
- [item]: [reason deferred]
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 · 57 lines · 34 tokens per session scan A 7f8489940dfa
implement is a skill published in the GitHub repository Kastalien-Research/thoughtbox (65 stars, last pushed 3mo ago), licensed MIT. It adds 34 tokens to every session and 425 once invoked, about $0.0001 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
laravel-testing
Use when testing controllers, services, or models, or implementing TDD on Laravel 13 with Pest 5 / PHPUnit 13 (or Pest 4 / PHPUnit 12 on PHP 8.3).
tdd
Use when writing production code that needs tests -- new features, bug fixes, refactoring. Enforces RED-GREEN-REFACTOR before implementation.
dev-pipeline
Issue → Explore → Plan → TDD (Red→Green→Refactor) → Benchmark → PR → Review.
testing
Comprehensive software testing skill covering unit tests, integration tests, TDD/BDD, mocking strategies, and test automation across multiple languages. Use this skill when writing test cases, designing test strategies, implementing test automation, or need guidance on testing frameworks and best practices. Ideal for…
Test Driven Development
Strict Red-Green-Refactor implementation methodology for high quality, regression-free software.
prespec
Write the behaviour specification for a feature BEFORE implementing it, as test cases. Use whenever you are about to build a new endpoint, screen, flow, or behaviour — especially anything touching auth, sessions, tokens, lists, or pagination. Also use when asked "how should I test this", "what should this actually…