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/workflows-worknpx skills add Kastalien-Research/thoughtbox --skill workflows-workgit 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 | $0.00026 | $0.00985 |
| Opus 5 | $0.00013 | $0.00492 |
| Sonnet 5 | $0.00005 | $0.00197 |
| Haiku 4.5 | $0.00003 | $0.00098 |
Grade A, and why
workflows-work 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 — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Execute the implementation plan: $ARGUMENTS
Purpose
You are executing Stage 4 (Implementation) of the development workflow. A plan exists from Stage 3 with decomposed tasks. Your job is to dispatch sub-agents for each task, collect their structured summaries, and persist everything to disk.
Pre-Conditions
Before starting, verify:
.workflow/state.jsonexists andcurrentStageis"implementation"- Plan file exists (check
stages.planning.artifacts.planin state, usually.workflow/plan.md)
If pre-conditions are not met, report what's missing and halt.
Process
Step 1: Read the Plan
Read .workflow/plan.md and the spec/ADR it references. Build the task execution order from the dependency graph.
Step 2: Dispatch Sub-Agents
For each task in dependency order:
-
Dispatch a sub-agent (use the Agent tool with
subagent_type: "general-purpose") with:- The task definition from the plan (files, acceptance criteria, notes)
- The relevant spec sections
- The ADR hypotheses this task should support/test
- Instructions to return the structured summary format (see below)
-
Parallelize independent tasks: If tasks have no dependency between them, dispatch their sub-agents concurrently using parallel Agent tool calls.
-
Persist the summary immediately upon receipt:
.workflow/summaries/<branch-slug>-<task-id>.md -
Verify acceptance criteria: Check each criterion from the plan against the sub-agent's summary. If any fail, note them for review.
Sub-Agent Summary Format
Each sub-agent MUST return this format:
## Sub-Agent Work Summary
### Task
- Branch: <current branch>
- Spec: <spec path>
### Changes
- Files modified: [list]
- Files created: [list]
- Lines: +N / -N
### Claims
1. "[specific testable claim]"
- Verifiable by: [test or command]
### Spec/Evidence Alignment
- H1 "<text>": SUPPORTS / REFUTES / NO EVIDENCE -- [evidence]
### Tests
- Tests written: N
- Tests passing: N/N
- Commands: `[exact command]`
### Known Gaps
- [anything deferred or uncertain]
### Risks
- [anything that could break other parts]
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 · 142 lines · 26 tokens per session scan A 96b00a1caec9
workflows-work is a skill published in the GitHub repository Kastalien-Research/thoughtbox (64 stars, last pushed 1mo ago), licensed MIT. It adds 26 tokens to every session and 985 once invoked, about $0.0001 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.