Theseus Protocol

VerifiedSafe

Thoughtbox-first Theseus workflow for behavior-preserving refactors. Use this when structure changes but behavior must stay fixed and scope drift needs hard boundaries.

Sby Skills Guide Bot
DevelopmentAdvanced
7/22/2026
Claude Code
#refactoring#thoughtbox#scope-control#mcp#code-mode

Recommended for

Automated summary

Drives a Thoughtbox-backed "Theseus" refactoring protocol that locks scope, tracks visas, and records checkpoints and outcomes as server-side state.

Strengths

  • Protocol state (scope, visas, audit history, terminal status) lives in Thoughtbox rather than local .theseus/ files
  • Test files and out-of-scope paths become write-locked after init, enforcing hard boundaries on the refactor
  • Only the coordinator calls tb.theseus, so audit or evidence gathering can be delegated to helper agents without breaking state
  • checkpoint/outcome operations leave a reusable record of successes, audit failures, and scope exhaustion

Limitations

  • Fully dependent on a Thoughtbox MCP server exposing thoughtbox_search/thoughtbox_execute and tb.theseus
  • Local fallbacks such as scripts/theseus.sh or implicit git reset --hard recovery are explicitly not supported
  • The multi-step protocol (init, visa, checkpoint, outcome) is heavy overhead for small or trivial changes
When to use it

Use it when code structure must change while behavior stays fixed and the blast radius needs explicit, enforceable boundaries.

When not to use it

Avoid it for greenfield feature work or exploratory edits where behavior is expected to change, or when no Thoughtbox server is available.

Security analysis

Safe
Quality score78/100

The skill is an instructional workflow layer around a remote protocol API. Its declared tools are read-only inspection (Read/Glob/Grep), subagent helpers, and two Thoughtbox MCP calls; there is no shell, no file mutation, no secret access, and no obfuscated payloads. It explicitly discourages relying on `git reset --hard` recovery. The only residual risk is implicit trust in the external Thoughtbox server and any hooks installed outside this file, which is a dependency concern rather than a destructive instruction.

Findings
  • •Delegates all state to an external MCP service (Thoughtbox `tb.theseus`) and assumes hooks consult that service before file writes; trust in that third-party server is inherited.
  • •Mentions hooks blocking writes and a `references/theseus-gate.md` enforcement design, but no write/bash/network primitives are in the declared toolset.
How this analysis is made

Examples

Start a behavior-preserving refactor
/theseus-protocol init scope: src/auth/session.ts, src/auth/tokens/ — description: extract token validation into its own module without changing any observable behavior
Request a scope visa
/theseus-protocol visa src/config/env.ts — the extracted validation module now imports env helpers, so the scope must expand to include it
Check status and close out
/theseus-protocol status, then record the outcome and complete with a summary of the structural yield achieved

name: theseus-protocol description: Thoughtbox-first Theseus workflow for behavior-preserving refactors. Use this when structure changes but behavior must stay fixed and scope drift needs hard boundaries. argument-hint: <init|visa|checkpoint|outcome|status|complete> [args] user-invocable: true allowed-tools: Read, Glob, Grep, Task, Agent, mcp__thoughtbox__thoughtbox_search, mcp__thoughtbox__thoughtbox_execute

Theseus Protocol

Theseus is a Thoughtbox-owned refactoring protocol.

The server-side Theseus implementation behind tb.theseus(...) owns scope, visa state, audit state, and terminal status. Claude Code hooks only ask Thoughtbox whether a write should be blocked.

Do not use .theseus/ files or scripts/theseus.sh as authoritative state. Do not rely on implicit git reset --hard recovery in the active workflow. Do not use legacy direct handles like thoughtbox_gateway or thoughtbox_theseus 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
  • Theseus operations: tb.theseus({ ... })

Each thoughtbox_execute call should contain at most one state-mutating Theseus operation. Read-only confirmation calls such as tb.theseus({ operation: "status" }) are safe to use for state checks.

Runtime Contract

  1. Protocol entry is explicit-only in v1.
  2. If you need schema or example confirmation, call thoughtbox_search before executing.
  3. Use thoughtbox_execute and call tb.theseus({ operation: ... }) for every protocol transition.
  4. Hooks consult Thoughtbox before mutating file operations.
  5. Hooks do not spawn agents or mutate protocol state.
  6. Helper agents may audit or gather evidence, but only the coordinator calls tb.theseus.

Commands

init

Required inputs:

  • Declared scope
  • Optional refactor description

Call:

async () => {
  return await tb.theseus({
    operation: "init",
    scope: ["src/module-a.ts", "src/module-b/"],
    description: "<refactor goal>",
  });
}

After init, test files are write-locked and out-of-scope writes require a visa.

visa

Required inputs:

  • Out-of-scope file path
  • Justification

Call:

async () => {
  return await tb.theseus({
    operation: "visa",
    filePath: "src/dependency.ts",
    justification: "<why the scope must expand>",
    antiPatternAcknowledged: true,
  });
}

This is the only supported way to expand scope in the active workflow.

checkpoint

Required inputs:

  • Diff hash or equivalent checkpoint identity
  • Atomic narrative
  • Cassandra verdict

Call:

async () => {
  return await tb.theseus({
    operation: "checkpoint",
    diffHash: "<diff hash>",
    commitMessage: "<atomic narrative>",
    approved: true,
    feedback: "<optional audit rationale>",
  });
}

Before checkpoint, you may optionally run a reviewer or judge agent to produce the Cassandra-style audit. That agent returns only a verdict and rationale. The coordinator records the outcome with tb.theseus.

outcome

Required inputs:

  • Whether validation passed
  • Optional details

Call:

async () => {
  return await tb.theseus({
    operation: "outcome",
    testsPassed: false,
    details: "<what failed>",
  });
}

The protocol records whether the refactor remains in a valid state. Recovery requirements are described by protocol state, not hidden local git resets.

status

Call:

async () => {
  return await tb.theseus({
    operation: "status",
  });
}

Use the returned state as the only source of truth for scope, visas, and audit history.

complete

Call:

async () => {
  return await tb.theseus({
    operation: "complete",
    terminalState: "complete",
    summary: "<what structural yield was achieved>",
  });
}

Completion should yield protocol closure plus reusable knowledge about successes, audit failures, or scope exhaustion.

Invariants

  1. Scope is explicit and server-owned.
  2. Test files are never modified during the refactor.
  3. Out-of-scope writes require a visa.
  4. Checkpoints are explicit and auditable.
  5. Audit evidence may come from helper agents, but state transitions belong to the coordinator.
  6. Knowledge capture includes failures, not just successful refactors.

Subagent Use

Use subagents only at explicit checkpoint phases.

Good uses:

  • Cassandra-style audit before checkpoint
  • Independent diff review for premature abstraction
  • Focused evidence gathering around a requested visa

Bad uses:

  • Hook-triggered subagents
  • Letting a helper agent call tb.theseus
  • Treating git rollback behavior as the protocol itself

References

  • Public MCP surface: thoughtbox_search, thoughtbox_execute
  • Theseus SDK call: tb.theseus({ operation: ... })
  • Durable context and thought trace: Thoughtbox session, thought, and knowledge operations through Code Mode
  • Protocol implementation: src/protocol/theseus-tool.ts
  • Enforcement design reference: references/theseus-gate.md

From the file to a first result

The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.

View the source and supporting files

This download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.

1. Download the file

Download SKILL.md

From the root of a test project, save the file as .skill-downloads/theseus-protocol-mrwaka1x/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.

Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.

mkdir -p '.skill-downloads/theseus-protocol-mrwaka1x' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/theseus-protocol-mrwaka1x/download' --output '.skill-downloads/theseus-protocol-mrwaka1x/SKILL.md.part' && mv '.skill-downloads/theseus-protocol-mrwaka1x/SKILL.md.part' '.skill-downloads/theseus-protocol-mrwaka1x/SKILL.md'

2. Check prerequisites

Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.

Tools declared by the author (check availability in your agent): Read, Glob, Grep, Task, Agent, mcp__thoughtbox__thoughtbox_search, mcp__thoughtbox__thoughtbox_execute

No recognized prerequisites section in this file. This does not mean it is self-contained: libraries, tools and access requirements may be mentioned elsewhere in the content or source repository.

The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.

3. Load the skill

After inspection, copy the complete folder into your project using one of the commands below, then open a new tool session. The command stops if a folder with the same name already exists: compare the files before replacing it.

Claude Code
test -f '.skill-downloads/theseus-protocol-mrwaka1x/SKILL.md' && test -s '.skill-downloads/theseus-protocol-mrwaka1x/SKILL.md' && mkdir -p '.claude/skills' && test ! -e '.claude/skills/theseus-protocol' && cp -R '.skill-downloads/theseus-protocol-mrwaka1x' '.claude/skills/theseus-protocol'

OpenSkills

OpenSkills must already be installed. The local install/read procedure is checked with OpenSkills 1.5.0, which requires Node.js ≥ 20.6.0. Catalog slugs are not resolved automatically.

Official OpenSkills installation
openskills install './.skill-downloads/theseus-protocol-mrwaka1x'

openskills read 'theseus-protocol-mrwaka1x'

Reading should display the installed file content and its base directory. It does not run the skill or install its dependencies.

For an agent that reads AGENTS.md, then sync the index. This command changes AGENTS.md: review the diff before using it.

openskills sync

Manual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.

4. Try a first task

Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:

Read .skill-downloads/theseus-protocol-mrwaka1x/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.

Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.

Related skills