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/workflownpx skills add Kastalien-Research/thoughtbox --skill workflowgit 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 | $0.01999 |
| Opus 5 | $0.00017 | $0.01000 |
| Sonnet 5 | $0.00007 | $0.00400 |
| Haiku 4.5 | $0.00003 | $0.00200 |
Grade A, and why
workflow 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 3d 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 — 206 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Orchestrate the development workflow for: $ARGUMENTS
Overview
You are the workflow conductor. You sequence 8 stages, enforce gates between them, dispatch to stage skills, and maintain a state file. You do NOT perform stage-specific work yourself — you delegate to the appropriate skill or sub-agent at each stage.
Stages and Dispatch
| # | Stage | Skill/Command | Gate (must pass before advancing) |
|---|---|---|---|
| 1 | Ideation | /workflow-ideation |
User confirms proceed (question 3d is not "confident no") |
| 2 | Dev-Time Docs | workflow Stage 2 (spec + claims) |
Spec in .specs/ with frontmatter claims per .schemas/spec-v1.json |
| 3 | Planning | /workflows-plan |
Plan file exists and user has approved it |
| 4 | Implementation | /workflows-work |
All sub-agent summaries persisted to disk, all tests pass |
| 5 | Review | /workflows-review |
All claims verified, no blocking findings |
| 6 | Revision | /workflow-revision |
Review passes OR max iterations reached + user accepts |
| 7 | Compound | /workflows-compound |
Learning captured |
| 8 | Reflection | /workflow-reflection |
Spec claims updated, issues closed, branch merged or marked ready |
Initialization
When invoked, first check for an existing workflow state:
cat .workflow/state.json 2>/dev/null
If state exists and is not completed: Resume from currentStage. Show the dashboard and ask the user whether to continue or restart.
If no state exists: Initialize a new workflow:
- Generate a short ID:
workflow-$(date +%s | tail -c 5) - Create or confirm the feature branch (per AGENTS.md branch rules)
- Write the initial state file (see State Schema below)
- Begin at Stage 1: Ideation
State Schema
Write to .workflow/state.json:
{
"id": "workflow-<short-id>",
"title": "<feature name from $ARGUMENTS>",
"branch": "<type>/<branch-name>",
"startedAt": "<ISO timestamp>",
"updatedAt": "<ISO timestamp>",
"currentStage": "ideation",
"stages": {
"ideation": { "status": "pending", "completedAt": null, "notes": "" },
"dev-docs": { "status": "pending", "artifacts": { "spec": null, "specClaims": null } },
"planning": { "status": "pending", "artifacts": { "plan": null } },
"implementation": { "status": "pending", "artifacts": { "summaries": [], "issues": [] } },
"review": { "status": "pending", "artifacts": { "findings": [] } },
"revision": { "status": "pending", "iterations": 0, "maxIterations": 3 },
"compound": { "status": "pending", "artifacts": { "solution": null } },
"reflection": { "status": "pending" }
}
}
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.
- 3d ago First seen · 206 lines · 34 tokens per session scan A 510368969876
workflow 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 1,999 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…
xcodebuildmcp-structured-output-review
Use when reviewing XcodeBuildMCP structured output schema changes, schema versioning, manifest outputSchema metadata, and JSON fixture compatibility.
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.…
cortex-automate
Set up automation — prospective memory triggers, neuro-symbolic rules, and CLAUDE.md sync. Use when the user says 'remind me when', 'trigger when', 'create a rule', 'auto-remember', 'sync to CLAUDE.md', 'push insights', 'set up trigger', 'when I open this file', 'when this keyword appears', or when you want to…
tabnexus-mcp-evals
Generate, validate, and run isolated Codex-to-TabNexus MCP evaluations with a curated 600-query dataset, executable gold tool labels, safety checks, and best-of-three stability scoring. Use when testing TabNexus MCP tool coverage, Agent behavior, regression quality, destructive-action safety, prompt changes, or a…
compare
Structured comparison of 2+ alternatives with consistent criteria and decision matrix.