Skip to main content
Glama

Checkpoint Codex Supervision

codex_checkpoint

Read or update a supervisor checkpoint to anchor the original goal, constraints, and acceptance criteria during long or complex tasks, preventing goal drift.

Instructions

Optional, bounded supervisor cognition memory keyed to one native Codex thread_id; the key is not a permanent task identity and does not require future work to remain on that thread. Use it to protect the original goal, constraints, and acceptance plus concise supervisor state during long or complex supervision when context dilution or goal drift makes an external anchor worthwhile. Initialization is not tied to crossing a ChatGPT window or round, starting another Codex turn, or switching native threads; initialize early when a task is already expected to be sufficiently long or complex for that protection. Do not use for one-shot work, and do not turn duration into a hard threshold: elapsed time, observe/poll count, token count, or mere silence are not automatic triggers. Later updates remain semantic-event driven and require a material change in understanding or root cause, constraint or scope interpretation, steering decision, user-authorized amendment or effective goal, or acceptance judgment or an explicit decision not to accept yet. Before final acceptance of a checkpointed task, read it once to re-anchor the original goal, constraints, acceptance, and current supervisor frame. This tool is optional and uncoupled from all other tools. Store concise supervisor summaries only; never prompts, transcripts, raw events, command output, final answers, or raw event streams. Updates preserve only immutable original plus bounded previous/current supervisor state.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
actionYesRead the checkpoint, or initialize/update it at a material supervisor decision point.
next_stepNoSingle next supervision step.
thread_idYesNative Codex thread id; no second task identifier is created.
original_goalNoConcise original user goal. Required only on initialization and immutable thereafter.
effective_goalNoCurrent effective goal after legitimate user amendments; defaults to original_goal on initialization.
current_decisionNoCurrent supervisor decision and why it matters.
acceptance_statusNoConcise acceptance assessment, not a task lifecycle or job status.
current_amendmentNoLatest concise user-authorized requirement amendment, or null to clear it, without changing the immutable original.
original_acceptanceNoConcise original acceptance criteria. Required only on initialization and immutable thereafter.
original_constraintsNoConcise original constraints. Required only on initialization and immutable thereafter.
current_understandingNoCurrent concise root-cause or task understanding.
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations only say readOnlyHint=false, but the description adds rich behavioral context: key semantics (not a permanent task identity), update triggers (semantic event, material change), storage restrictions (never prompts/transcripts), and the requirement to read before final acceptance. This goes far beyond the annotations and is consistent with them.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is longer than average (~180 words), but every sentence earns its place by covering purpose, usage, exclusions, storage policy, and update semantics. It is well-structured, with clear statements and prohibitions, though some length could be trimmed without losing content.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (11 parameters, multiple update conditions, acceptance process), the description is complete: it explains when to use, what to store, how updates work, and the read-before-acceptance rule. No output schema is present, but the description focuses on behavior and constraints, which is sufficient for an agent to use it correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema already describes all 11 parameters (100% coverage). The description adds semantic meaning beyond the schema by explaining the immutable-vs-mutable distinction (original vs current/effective goal, original constraints, etc.), what should not be stored, and the relationship between parameters like original and effective goals. This adds value without repeating schema details.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: an optional, bounded supervisor cognition memory keyed to a Codex thread_id, used to protect the original goal, constraints, acceptance, and supervisor state. It distinguishes this tool from siblings by emphasizing it is uncoupled and optional, and by being specific about its function as a checkpoint for supervision context.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives explicit when-to-use guidance (long/complex supervision with context dilution or goal drift) and when-not-to-use guidance (one-shot work, no hard duration thresholds). It also notes the tool is optional and uncoupled from other tools, helping an agent decide when to invoke it versus alternatives.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/zoeynine/Local-Codex-Bridge'

If you have feedback or need assistance with the MCP directory API, please join our Discord server