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/ulysses-protocolnpx skills add Kastalien-Research/thoughtbox --skill ulysses-protocolgit 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/ulysses-protocol)<a href="https://agentmods.dev/skills/kastalien-research/thoughtbox/ulysses-protocol"><img src="https://agentmods.dev/badge/skills/kastalien-research/thoughtbox/ulysses-protocol.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 5.1 | $0.00042 | $0.01973 |
| Opus 5 | $0.00021 | $0.00986 |
| Sonnet 5 | $0.00008 | $0.00395 |
| Haiku 4.5 | $0.00004 | $0.00197 |
Grade A, and why
ulysses-protocol 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 6d 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 — 263 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ulysses Protocol
Ulysses is a Thoughtbox-owned debugging protocol.
The invariants live in the server-side Ulysses implementation behind
tb.ulysses(...).
The durable trace lives in Thoughtbox thoughts and knowledge.
Codex hooks only enforce the current server state.
Do not use .ulysses/ files or scripts/ulysses.sh as authoritative state.
Do not use legacy direct handles like thoughtbox_gateway or thoughtbox_ulysses
as the interaction surface when Code Mode is available.
API Surface
The current public Thoughtbox MCP surface is Code Mode:
- Discovery:
thoughtbox_search - Execution:
thoughtbox_execute - Ulysses operations:
tb.ulysses({ ... }) - Validator notebook setup:
tb.notebook.create(...)andtb.notebook.addCell(...)
Each thoughtbox_execute call should contain at most one state-mutating
Ulysses operation. Read-only confirmation calls such as
tb.ulysses({ operation: "status" }) are safe to use for state checks.
Example execution wrapper:
async () => {
return await tb.ulysses({
operation: "status",
});
}
Runtime Contract
- Protocol entry is explicit-only in v1.
- If you need schema or example confirmation, call
thoughtbox_searchbefore executing. - Use
thoughtbox_executeand calltb.ulysses({ operation: ... })for every protocol transition. - Hooks may block mutating work when the server reports
S=2; read-only inspection remains allowed. - Helper agents may gather evidence after
reflect, but only the coordinator callstb.ulysses.
Commands
init
Required inputs:
- Problem statement
- Optional constraints
Call:
async () => {
return await tb.ulysses({
operation: "init",
problem: "<problem>",
constraints: ["<optional constraint>"],
});
}
Then record a structured Thoughtbox thought summarizing the debugging context.
plan
Required inputs:
- Primary action
- Recovery action
- Primary validator: a notebook code cell that decides the primary step's outcome
- Recovery validator: a notebook code cell that decides the recovery step's outcome
- Optional
irreversible
What ships with it
3 files 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.
- 6d ago First seen · 263 lines · 42 tokens per session scan A 1c90523d3f90
ulysses-protocol is a skill published in the GitHub repository Kastalien-Research/thoughtbox (64 stars, last pushed 1mo ago), licensed MIT. It adds 42 tokens to every session and 1,973 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
unity-console
Capture and query the Unity Editor console.
report-issue-local
File a bug or feature request against this MCP server's own repo. Use for server-specific issues — tool logic, service integrations, config problems, or domain bugs that aren't caused by the framework.
unity-debug
Inspect debug, diagnostics and compile state.
Reverse Engineering & Binary Analysis
Binary analysis, assembly interpretation, disassembly, decompilation, firmware RE, and protocol reverse engineering.
watch
Watch a rendered video (whole file or specific ranges) at a chosen fidelity and emit a timestamp-keyed observation report. Observation only — no edits, no verdicts.
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.…