goal-governor

goal-governor is a skill for Codex from jscraik/Agent-Skills. It costs 64 tokens per session (1,963 once invoked), scanned A, original, Apache-2.0.

A task-management guide for durable Codex goals that have a visible board recording objectives, progress, evidence, and blockers.

In plain words
What is it for?
Use it to create, continue, inspect, repair, or close governed goals and classify why a task has not finished.
Why use it?
It helps detect stalled or inconsistent goal state and keeps reported progress aligned with the task records.

Skill for Codex

Written for Codex: agents/openai.yaml present. Also seen: mentions Codex.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is ./bin/ask skills audit Skills/agent-ops/goal-governor --level strict --json --robot.

Good fit Use it to create, continue, inspect, repair, or close governed goals and classify why a task has not finished.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/jscraik/Agent-Skills
agentmods
npx agentmods add skills/jscraik/agent-skills/goal-governor

Made for: Codex.

Wrote 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.

agentmods badge for goal-governor

README.md
[![agentmods](https://agentmods.dev/badge/skills/jscraik/agent-skills/goal-governor/github.svg)](https://agentmods.dev/skills/jscraik/agent-skills/goal-governor)
Your own site
<a href="https://agentmods.dev/skills/jscraik/agent-skills/goal-governor"><img src="https://agentmods.dev/badge/skills/jscraik/agent-skills/goal-governor/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.

agentmods 80×15 button for goal-governor

Your own site · 80×15
<a href="https://agentmods.dev/skills/jscraik/agent-skills/goal-governor"><img src="https://agentmods.dev/badge/skills/jscraik/agent-skills/goal-governor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 64 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,963 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, 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 System Prompt Leakage · line 55
    Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.
    Fix: Remove any instructions that reveal, print, or output system prompts or internal rules. System instructions should never be exposed to end users.
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00064 $0.01963
Opus 5 $0.00032 $0.00981
Sonnet 5 $0.00013 $0.00393
Haiku 4.5 $0.00006 $0.00196

Measured 9d ago against content hash 5445fabb4470, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

goal-governor 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 9d ago.

The scan reads SKILL.md. This mod also ships 4 executable files (scripts/check_goal_board_impl.py, scripts/check_goal_board.py, scripts/write_pr_triage_report.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Skills/agent-ops/goal-governor/SKILL.md · 156 lines

How it starts

The opening of the file, as written. The whole thing — 156 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Goal Governor

When To Use

Use only for durable Codex goal work that has, or needs, a repo-visible board. Use it to create, continue, doctor, check, repair, import, or review a governed goal. Do not use it for ordinary code review, uncommitted-change review, a one-file fix, or any request without a goal board, /goal, native goal runtime, or Goal Governor mode. For an ordinary review, do not write goal-governor-output.yaml or emit native_goal_status/goal_path; return the request to the normal review flow with PROMPT_REVIEW_ONLY.

Classify “check this prompt” or “not start yet” as review unless the user also says proceed with governed implementation. Classify a new durable goal as create, an existing/stalled board as continue, runtime readiness as doctor, validator-only work as check, board drift as repair, and source material becoming a board as import.

Inputs

  • Project instructions plus a goal prompt or selected board path.
  • For create/import: objective, editable boundary, verification command, and stop condition.
  • For continuation/closeout: goal.md, state.yaml, receipts.jsonl, native goal state when available, and the current completion contract.

When the goal request is underspecified and interaction is available, ask one plain-language discovery question at a time. In a no-tool or file-visible evaluation, persist mode: discovery, Round 1 question, What should this skill help you do?, and Why this matters in the output contract.

Outputs

Return YAML with schema_version, mode, goal_path, native_goal_status, board_status, next_action, truth_lanes, receipt_closure_ledger, continuation_gate, native_blocker_audit, validation_evidence, and risks. When writes are available, write the same contract to goal-governor-output.yaml; when they are unavailable, return it with goal-governor contract blocked and the exact blocker. In review mode, return prompt readiness only.

Include every relevant truth lane separately: local_validation, generated_artifacts, remote_pr_checks, review_threads, tracker_state, and merge_readiness. A passing lane does not infer another lane.

Read the full file on GitHub · 156 lines

Changes

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.

  1. 9d ago First seen · 156 lines · 64 tokens per session scan A 5445fabb4470

Subscribe to this mod's changes

goal-governor is a skill published in the GitHub repository jscraik/Agent-Skills (8 stars, last pushed 11d ago), licensed Apache-2.0. It adds 64 tokens to every session and 1,963 once invoked, about $0.0003 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 2026-09-03.