goal-bridge

goal-bridge is a skill for Claude Code from arbazkhan971/godmode. It costs 41 tokens per session (581 once invoked), scanned A, original, MIT.

A guide for writing machine-checkable completion contracts for agent goals. Each contract defines a command, a threshold, an evidence file, and a condition for rolling back the work.

In plain words
What is it for?
Use it to define success metrics for automated tasks, record proof of progress, and specify when a goal should be considered failed or reverted.
Why use it?
It turns a vague statement that work is finished into a testable result that can be checked consistently. This makes it easier to detect failure and decide when to undo changes.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the godmode plugin — 132 skills, 1 command, 7 agents, 3 MCP servers shipped together

Good fit Use it to define success metrics for automated tasks, record proof of progress, and specify when a goal should be considered failed or reverted.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/arbazkhan971/godmode/goal-bridge
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.

Any agent
npx skills add arbazkhan971/godmode --skill goal-bridge
Clone the repo
git clone --depth 1 https://github.com/arbazkhan971/godmode

Made for: Claude Code.

Or install godmode, the plugin that ships this one along with the rest of its 132 skills, 1 command, 7 agents, 3 MCP servers.

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-bridge

README.md
[![agentmods](https://agentmods.dev/badge/skills/arbazkhan971/godmode/goal-bridge/github.svg)](https://agentmods.dev/skills/arbazkhan971/godmode/goal-bridge)
Your own site
<a href="https://agentmods.dev/skills/arbazkhan971/godmode/goal-bridge"><img src="https://agentmods.dev/badge/skills/arbazkhan971/godmode/goal-bridge/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-bridge

Your own site · 80×15
<a href="https://agentmods.dev/skills/arbazkhan971/godmode/goal-bridge"><img src="https://agentmods.dev/badge/skills/arbazkhan971/godmode/goal-bridge.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 41 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 581 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: 2 findings, 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 Tool Misuse · line 39
    Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).
    Fix: Validate all tool parameters against an allowlist. Reject dangerous parameter values (shell=True, --force, -rf /) and use safe defaults.
  • medium Agent Snooping · line 65
    Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
    Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 $0.00041 $0.00581
Opus 5 $0.00020 $0.00291
Sonnet 5 $0.00008 $0.00116
Haiku 4.5 $0.00004 $0.00058

Measured 6d ago against content hash e3cd9b70ee7a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

goal-bridge 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.

skills/goal-bridge/SKILL.md · 66 lines

How it starts

The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Goal-Bridge — Completion Contracts for Goal Modes

Activate When

  • User invokes /godmode:goal-bridge
  • User sets a goal in a harness goal mode (/goal or your harness's equivalent)
  • User asks "how do we know this is done"
  • An evaluator needs a command that exits 0

Workflow

Step 1: Derive the Contract BEFORE Execution

No work starts until the contract exists. Derive all four fields up front:

  • metric — ONE shell command where exit 0 = goal met. Never prose judgment.
  • threshold — numeric or boolean bound the metric must satisfy.
  • evidence — file path where metric output/proof is written every round.
  • rollback — exact trigger that reverts the work.

Step 2: Emit the Contract Block

Single source of truth — use EXACTLY this shape everywhere:

Goal-Bridge Contract (mandatory final output):
- metric: <single shell command; contract met iff it exits 0>
- threshold: <numeric or boolean bound the metric must satisfy>
- evidence: <file path where metric output/proof is written every round>
- rollback: <exact trigger that reverts the work, e.g. "metric fails on 2 consecutive rounds">

Step 3: Run the Metric Every Round

Each round: run the metric command and append its output to the evidence path.

Step 4: Rollback on Trigger

git reset --hard <last-good-commit>

Then log the attempt: what failed, which round, evidence excerpt.

Step 5: Hand Off the Contract

Give the contract block to the harness goal mode / evaluator (/goal or your harness's equivalent). The evaluator consumes "command exits 0".

Hard Rules

  1. The contract exists BEFORE work starts.
  2. The metric is a single command, never prose judgment.
  3. The evidence file is written every round.
  4. Never declare done without exit 0.

Stop Conditions

STOP when FIRST of:
  - metric exits 0 AND evidence written -> DONE
  - rollback trigger fires -> revert + report PARTIAL
  - cannot express goal as exit-0 command -> report NEEDS_CONTEXT (do NOT fake a metric)

Read the full file on GitHub · 66 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. 6d ago First seen · 66 lines · 41 tokens per session scan A e3cd9b70ee7a

Subscribe to this mod's changes

goal-bridge is a skill published in the GitHub repository arbazkhan971/godmode (26 stars, last pushed 12d ago), licensed MIT. It adds 41 tokens to every session and 581 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 2026-09-03.

Related

Other skills, from other repositories

asc-subscription-localization

Bulk-localize subscription, subscription-group, and in-app purchase display names across App Store locales using asc, including API 4.4.1 version-scoped v2 resources. Use when filling or updating subscription/IAP names and descriptions without App Store Connect UI work.

rorkai/app-store-connect-cli-skills · 60 tokens

jobs-to-be-done

Discover what customers truly need by analyzing the "job" they hire your product to do. Use when the user mentions "customer discovery", "why customers churn", "what job does this solve", "competing against luck", "product-market fit", "switching behavior", "milkshake moment", or "functional vs emotional jobs". Also…

wondelai/skills · 137 tokens

agent-code-generator

Generates Agent definitions (.md files) based on user intent and standard templates.

majiayu000/claude-skill-registry · 20 tokens

scienceworld-growth-focuser

Use when you have planted a seed or need to track a plant's growth stage (sprouting, flowering, reproduction). Applies the 'focus on' action to a specific plant or biological entity to signal intent and monitor its development. Trigger after planting or when you need to observe life cycle progression in the…

zjunlp/SkillNet · 71 tokens

codex

Run benchmark-selected GPT-5.6 work through the Codex CLI.

notque/vexjoy-agent · 18 tokens

iterate-pivot-decision

Documents a strategic pivot or persevere decision with the evidence, analysis, and rationale. Use when evaluating whether to change direction on a product, feature, or strategy based on market feedback.

product-on-purpose/pm-skills · 43 tokens