goal-conductor

goal-conductor is a skill for Claude Code, Codex from kirodotdev/KiroCrew. It costs 105 tokens per session (5,389 once invoked), scanned A, original, Apache-2.0.

A coordinator for large, long-running goals that splits the work into independent items and tracks their progress. It starts one top-level session for each item and decides what should happen next.

In plain words
What is it for?
Use it for goals such as clearing a flaky-test backlog, where separate work items can be dispatched, monitored, and verified.
Why use it?
It keeps a broad project from becoming one unmanageable task and checks whether each item has met its completion condition.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

About the project

Kiro Crew is a persistent development workspace where agents continue multi-step software work across sessions, schedules, and connected interfaces. Developers use it locally or remotely through a desktop app, web dashboard, CLI, Slack, or Discord, with unattended tasks and recurring jobs. The catalogue contains skills and instructions for working with this workspace.

kirodotdev/KiroCrew · 3,667 stars · on GitHub · kiro.dev

Install

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.

agentmods
npx agentmods add skills/kirodotdev/kirocrew/goal-conductor
Any agent
npx skills add kirodotdev/KiroCrew --skill goal-conductor
Clone the repo
git clone --depth 1 https://github.com/kirodotdev/KiroCrew

Made for: Claude Code, 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-conductor

README.md
[![agentmods](https://agentmods.dev/badge/skills/kirodotdev/kirocrew/goal-conductor.svg)](https://agentmods.dev/skills/kirodotdev/kirocrew/goal-conductor)
Your own site
<a href="https://agentmods.dev/skills/kirodotdev/kirocrew/goal-conductor"><img src="https://agentmods.dev/badge/skills/kirodotdev/kirocrew/goal-conductor.svg" alt="Measured on agentmods" height="20"></a>
Per session 105 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 5,389 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00105 $0.05389
Opus 5 $0.00053 $0.02694
Sonnet 5 $0.00021 $0.01078
Haiku 4.5 $0.00011 $0.00539

Measured today against content hash 94f2612cf697, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

goal-conductor 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 today.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/accept_eval.py, scripts/ledger_entry.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.

src/kiro_crew/builtin_skills/goal-conductor/SKILL.md · 397 lines

How it starts

The opening of the file, as written. The whole thing — 397 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Goal Conductor

You own a goal. You do not do the goal's work.

Your four jobs, none of which can be delegated to a work item:

  1. Decompose the goal into work items.
  2. Stand up a session per item and record it in the ledger.
  3. Verify what came back.
  4. Decide the next round, or stop.

Everything else belongs in a work item. This spec has no fs_write — that is deliberate. If a task needs a file written, it is a work item, not something you do. execute_bash IS granted, for exactly one purpose: running this skill's bundled scripts — the acceptance evaluator (scripts/accept_eval.py) and the ledger entry codec (scripts/ledger_entry.py). Both are deliberately kept out of allowedTools, so every call prompts for approval — see "Known limits" for what that costs per patrol cycle.

What is a work item

A candidate qualifies only if all three hold:

  1. Independent — it does not consume another candidate's output. Two candidates that hand off to each other are one sequence inside a single item.
  2. Assertable — you can name its completion condition now, before dispatching, as one of the evaluator's kinds: pr_checks (a PR's checks all green via gh), file (a path existing), or human_approval (the user accepts it — legitimate for design reviews and go/no-go gates, but never machine-evaluated). There is deliberately no "run this command" kind, so "the test suite passes" is expressed as pr_checks on the PR that carries the work — CI runs the suite, and its verdict is the one that counts. If an item's completion genuinely cannot be stated as one of these, it is not assertable: say so and treat it as a needs-human item rather than inventing a condition.
  3. Long-running — long enough that the user would plausibly want to open it and steer it while it runs.

Fewer than two qualifying candidates means the goal does not need you. Say so and just do the work in this session.

The boundary rule

If a candidate's input is the ledger's current state, and its output is "what to do next" or "a summary of what happened", it is YOUR job, not a work item.

Read the full file on GitHub · 397 lines

Files

What ships with it

2 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.

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. today Changed · +8 lines 94f2612cf697
  2. yesterday Changed · +2 lines f3e77eb83b9f
  3. 4d ago Changed · -17 lines 14c351d5049c
  4. 6d ago First seen · 404 lines · 105 tokens per session scan A b590fad9fd8a

Subscribe to this mod's changes

goal-conductor is a skill published in the GitHub repository kirodotdev/KiroCrew (3,667 stars, last pushed today), licensed Apache-2.0. It adds 105 tokens to every session and 5,389 once invoked, about $0.0005 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.