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-compoundnpx skills add Kastalien-Research/thoughtbox --skill workflows-compoundgit 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/workflows-compound)<a href="https://agentmods.dev/skills/kastalien-research/thoughtbox/workflows-compound"><img src="https://agentmods.dev/badge/skills/kastalien-research/thoughtbox/workflows-compound.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00023 | $0.00986 |
| Opus 5 | $0.00012 | $0.00493 |
| Sonnet 5 | $0.00005 | $0.00197 |
| Haiku 4.5 | $0.00002 | $0.00099 |
Grade A, and why
workflows-compound 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 4d 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 — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Capture learnings from the current workflow: $ARGUMENTS
Purpose
You are executing Stage 7 (Compound) of the development workflow. Implementation is reviewed and revised. Your job is to extract reusable learnings from this workflow and persist them so future workflows benefit. You are NOT writing code — you are documenting what was learned.
Pre-Conditions
Before starting, verify:
.workflow/state.jsonexists andcurrentStageis"compound"- Review has passed (check
stages.review.statusis"completed") - If revision happened, it's also completed
If pre-conditions are not met, report what's missing and halt.
Process
Step 1: Gather Evidence
Read all workflow artifacts:
- Workflow state:
.workflow/state.json— timeline, iterations, stage notes - Sub-agent summaries:
.workflow/summaries/*.md— what was built - Review report:
.workflow/review-report.md— what was found - Spec and ADR: The original design documents
- Git log: What actually changed
git log --oneline --since="$(jq -r .startedAt .workflow/state.json)" -- .
Step 2: Extract Learnings
Identify three categories of learnings:
Solutions — Reusable patterns for solving specific problems:
- What problem was solved?
- What approach worked?
- What approach was tried and didn't work?
- What would you do differently next time?
Discoveries — Things learned about the codebase or domain:
- Unexpected behaviors encountered
- Undocumented constraints discovered
- Performance characteristics measured
Process — What worked or didn't in the workflow itself:
- Which stages were smooth vs. painful?
- Where did revision loops happen and why?
- What spec assumptions were wrong?
Step 3: Write Solution Document
If a reusable solution was produced, write it to docs/solutions/:
# <Problem Title>
## Problem
[What problem this solves, in 2-3 sentences]
## Solution
[The approach that worked, with code references]
## Context
- Workflow: <id>
- Spec: <path>
- Date: <ISO date>
## Key Decisions
- [Decision 1]: [Why this choice was made]
- [Decision 2]: [Why this choice was made]
## What Didn't Work
- [Approach that was tried and abandoned, with brief explanation]
## Related
- [Links to specs, ADRs, or other solutions]
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.
- 4d ago First seen · 137 lines · 23 tokens per session scan A 327455bdaa0b
workflows-compound is a skill published in the GitHub repository Kastalien-Research/thoughtbox (64 stars, last pushed 1mo ago), licensed MIT. It adds 23 tokens to every session and 986 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
unity-addressables
Manage Addressables groups, entries, profiles and content builds (com.unity.addressables, reflection-based).
impeccable
Use when the user wants to design, redesign, shape, critique, audit, polish, clarify, distill, harden, optimize, adapt, animate, colorize, extract, or otherwise improve a frontend interface. Covers websites, landing pages, dashboards, product UI, app shells, components, forms, settings, onboarding, and empty states.…
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…
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 brand-color canvas, hard-concatenated in order, closed on a deterministic Playwright brand end card, and mixed under one instrumental bed at…
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.…
Threat Hunting & IOC Analysis
IOC extraction, threat intelligence correlation, MITRE ATT&CK mapping, hunt hypothesis generation, and detection rule creation.