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 agentmods add skills/kastalien-research/thoughtbox/implementnpx skills add Kastalien-Research/thoughtbox --skill implementgit clone --depth 1 https://github.com/Kastalien-Research/thoughtboxWhat 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 | $0.00034 | $0.00425 |
| Opus 5 | $0.00017 | $0.00212 |
| Sonnet 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 2d 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.
- 2d ago First seen · 57 lines · 34 tokens per session scan A 7f8489940dfa
implement 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 425 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
reasoning
Use BEFORE answering analytical, diagnostic, planning, or multi-step reasoning questions. Trigger phrases include "should I X or Y", "why is X happening", "what's the best approach", "what are the tradeoffs", "help me think through", "diagnose", "root cause", "plan/design X", "what are the implications of", "compare…
opik-diagnose
Surface the Opik traces worth a developer's attention, ranked by signal — errors, failed tool calls, latency, regressions, and low online-eval scores — plus Diagnostics issues. Reads live/production traces via the SDK (searchtraces and agentinsights) and works with no MCP; uses the MCP issue entity when connected.…
client-scripts
Write ServiceNow client scripts (onLoad/onChange/onSubmit/onCellEdit) using gform, guser, GlideAjax, field visibility/mandatory toggles, and validation with debounced server calls.
agoragentic-transaction-assurance
Prepare, evaluate, and reconcile autonomous agent transactions without self-granting payment or owner authority. Use when an agent must bind principal authority, seller terms, payment evidence, execution, delivered outcome, and reconciliation; handle paid retries safely; or prepare an authority request for owner…
linkding
Manage bookmarks with Linkding. Use when the user asks to "save a bookmark", "add link", "search bookmarks", "list my bookmarks", "find saved links", "tag a bookmark", "archive bookmark", "check if URL is saved", "list tags", "create bundle", or mentions Linkding bookmark management.
maya-shot-export
Pipeline stage — shot-level export: frame ranges, cameras, FBX / Alembic packaging for editorial. Use when packaging shot data for downstream departments. Not for full pipeline publish (maya-pipeline) or scene assembly (maya-scene-assembly).