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 ulc-loopgit 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/ulc-loop)<a href="https://agentmods.dev/skills/kastalien-research/thoughtbox/ulc-loop"><img src="https://agentmods.dev/badge/skills/kastalien-research/thoughtbox/ulc-loop/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/ulc-loop"><img src="https://agentmods.dev/badge/skills/kastalien-research/thoughtbox/ulc-loop.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Agent Snooping · line 33 Skill reads from agent configuration directories (.claude/, .codex/, .gemini/). These directories may contain API keys, personal settings, and other credentials that the skill has no legitimate need to access.Fix: Remove all code or instructions that access agent configuration directories (.claude/, .codex/, .gemini/). If configuration values are needed, pass them explicitly as parameters or environment variabl
- high Agent Snooping · line 52 Skill reads from agent configuration directories (.claude/, .codex/, .gemini/). These directories may contain API keys, personal settings, and other credentials that the skill has no legitimate need to access.Fix: Remove all code or instructions that access agent configuration directories (.claude/, .codex/, .gemini/). If configuration values are needed, pass them explicitly as parameters or environment variabl
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 | $0.00035 | $0.00788 |
| Opus 5.5 | $0.00014 | $0.00315 |
| Sonnet 5.5 | $0.00007 | $0.00158 |
| Haiku 4.5 | $0.00003 | $0.00079 |
Grade A, and why
ulc-loop 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.
How it starts
The opening of the file, as written. The whole thing — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ULC Loop
Start an autonomous improvement loop powered by Ralph Wiggum.
Setup
Parse arguments from: $ARGUMENTS
Defaults:
--budget: 5 (USD)--max-iterations: 20
Workflow
Step 1: Pre-flight Checks
-
Verify Ralph Wiggum plugin is installed:
ls .Codex/plugins/cache/Codex-plugins/ralph-wiggum/ 2>/dev/null || echo "NOT INSTALLED"If not installed, tell the user to run:
Codex plugin install ralph-wiggum@Codex-plugins -
Check for existing Ralph loop:
cat .Codex/ralph-loop.local.md 2>/dev/null && echo "ACTIVE" || echo "INACTIVE"If ACTIVE, warn: "A Ralph loop is already running. Run
/cancel-ralphfirst." -
Check git state is clean:
git status --porcelainIf dirty, warn and suggest committing first.
Step 2: Read the ULC Prompt
Read the ULC decision procedure from .Codex/skills/ulc-loop/ulc-prompt.md.
Step 3: Initialize ULC State
Create the initial ULC state file if it doesn't exist:
cat > .Codex/ulc-state.local.json << 'EOF'
{
"iteration": 0,
"cumulative_cost_usd": 0,
"budget_usd": <BUDGET>,
"actions": [],
"exploration_misses": 0,
"started_at": "<ISO timestamp>"
}
EOF
Replace <BUDGET> with the parsed budget value.
Step 4: Create Ralph State File
Write .Codex/ralph-loop.local.md with YAML frontmatter and the ULC prompt as the body:
---
active: true
iteration: 1
max_iterations: <MAX_ITERATIONS>
completion_promise: "BUDGET EXHAUSTED OR ALL WORK COMPLETE"
started_at: "<ISO timestamp>"
---
<contents of ulc-prompt.md>
Step 5: Confirm and Start
Output:
ULC Loop activated via Ralph Wiggum.
Budget: $<budget> USD
Max iterations: <max_iterations>
Completion promise: "BUDGET EXHAUSTED OR ALL WORK COMPLETE"
The loop will:
1. Check backlog for ready work
2. Dispatch sub-agents for substantial tasks
3. Explore via QD when backlog is empty
4. Stop when budget is exhausted or all work is complete
State file: .Codex/ulc-state.local.json
Ralph state: .Codex/ralph-loop.local.md
Starting first OODA cycle...
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 113 lines · 35 tokens per session scan A 6a8325b765b9
ulc-loop is a skill published in the GitHub repository Kastalien-Research/thoughtbox (65 stars, last pushed 3mo ago), licensed MIT. It adds 35 tokens to every session and 788 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
matlab
Builds, reviews, migrates, and plans MATLAB or GNU Octave numerical workflows. Use for arrays, tabular/time data, tests, projects, graphics, MAT files, and explicit Python interoperability.
phylogenetics
Builds and analyzes phylogenetic trees using MAFFT multiple sequence alignment, IQ-TREE maximum likelihood with ModelFinder and branch support, and FastTree approximate inference. Uses ETE3 for tree summaries and visualization. Applies to homologous nucleotide or protein sequences, microbial gene trees, protein…
unity-yaml-editing
Last-resort guidance for safely hand-editing Unity YAML.
ad-policy-check
Checks paid ads against the ad platform's rules (Meta, TikTok, Google, LinkedIn and others) and the brand's category rules: the copy, on-image or on-screen text, pictures and people. Rewrites what can be fixed honestly, adds the disclosures that are needed, and flags anything that needs a human or legal review, with…
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 chosen backdrop colour, hard-concatenated in order, closed on a deterministic Playwright brand end card, and mixed under one instrumental bed…
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…