A skill for resuming a paused goal managed by the gk command-line tool. It checks the goal's state and continues it when the recorded blocker has been cleared.

Use it after manually fixing a blocker, to resume an active or parked goal, or to decide how to continue after repeated rejection.

It prevents a paused goal from being resumed blindly and handles goals waiting for human input or previously rejected by a reviewer.

goal-resume — Skill for Claude Code by bonfire-systems

Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code

/plugin marketplace add bonfire-systems/goalkeeper

Claude Code

/plugin install goalkeeper

Made for: Claude Code.

Or install goalkeeper, the plugin that ships this one along with the rest of its 8 skills, 1 hook.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/bonfire-systems/goalkeeper/goal-resume/github.svg)](https://agentmods.dev/skills/bonfire-systems/goalkeeper/goal-resume)

Your own site

<a href="https://agentmods.dev/skills/bonfire-systems/goalkeeper/goal-resume"><img src="https://agentmods.dev/badge/skills/bonfire-systems/goalkeeper/goal-resume/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/bonfire-systems/goalkeeper/goal-resume"><img src="https://agentmods.dev/badge/skills/bonfire-systems/goalkeeper/goal-resume.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 560 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.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00041	$0.00560
Opus 5	$0.00020	$0.00280
Sonnet 5	$0.00008	$0.00112
Haiku 4.5	$0.00004	$0.00056

Measured 12d ago against content hash 870a3fb20e04, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

goal-resume 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 12d 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-resume/SKILL.md · 29 lines

What it actually says

You are operating the goal-resume skill. The gk CLI is python3 "${CLAUDE_PLUGIN_ROOT}/scripts/gk.py", abbreviated gk.

Flow

Run gk status. It shows the active goal (if any) and the Parked queue — parked goals hold no slot, so "no active goal" does not mean "nothing to resume." If the user named a goal, target it; otherwise the active goal, or the single parked goal if that is unambiguous. Nothing to resume → tell the user and stop.
Branch on the target's status:
- active — already running; gk resume will say so. No-op.
- done — goals don't reopen; suggest /goal-clear to archive, then a new contract.
- paused — run gk resume --keep-count.
- needs_human, rejection count 0 (parked on a human-gated blocker) — confirm the recorded needs is actually provided, then gk resume <slug>.
- needs_human, rejections > 0 (judge rejected too many times) — Ask the user via AskUserQuestion whether to:
  - Reset rejection counter and continue (Recommended) — user confirms they fixed the flagged issues → gk resume <slug> --reset-rejections.
  - Continue without reset — one more rejection re-parks it → gk resume <slug> --keep-count.
  - Abandon — route to /goal-clear.
gk refuses a bare resume in that case precisely so this question cannot be skipped.
gk restores the slot and, if the goal heads a waiting chain, re-arms the chain. If another goal holds the slot, gk refuses — finish, park, or clear that one first (one loop at a time).
On success, re-enter the goal skill execution loop immediately. Do not just schedule a wakeup — do real work in this turn. If the goal is a chain link (see gk status), re-spawn the executor subagent per goal-chain/SKILL.md instead.

Hard rules

Never silently reset the rejection counter — the AskUserQuestion step is mandatory for needs_human (and gk enforces the explicit flag).
Never resume a done goal.

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.

12d ago First seen · 29 lines · 41 tokens per session scan A 870a3fb20e04

Subscribe to this mod's changes

goal-resume is a skill published in the GitHub repository bonfire-systems/goalkeeper (13 stars, last pushed 12d ago), licensed MIT. It adds 41 tokens to every session and 560 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 2026-08-30.

Autonomous Agents Claude Code Planning agents ai-agents anthropic automation

hive.slack-notifications-setup

Set up a Slack notification channel (Sentinel) for a colony by driving the browser — reuse or create the "Hive Sentinel" Slack app from a JSON manifest, install it, capture the bot + app tokens, create/select the channel via the Slack API, and turn Sentinel on so the colony can ping the user on Slack and accept…

aden-hive/hive · 136 tokens

hive.pdf

Read, write, merge, split, rotate, watermark, encrypt, and OCR PDF files using Python (pypdf, pdfplumber, reportlab, pypdfium2) and command-line tools (poppler-utils, qpdf). Use when the user asks to extract text/tables/images from a PDF, create or modify a PDF, combine or split PDFs, OCR a scanned PDF…

aden-hive/hive · 98 tokens

hive.chart-creation-foundations

Required reading whenever any chart tool is available. Teaches the one-tool embedding contract (call chartrender → live chart appears in chat AND a downloadable PNG lands in the queen session dir), the ECharts (data viz) vs Mermaid (structural diagrams) decision, the BI/financial-grade aesthetic baseline (no…

aden-hive/hive · 133 tokens

browser-edge-cases

SOP for debugging browser automation failures on complex websites. Use when browser tools fail on specific sites like LinkedIn, Twitter/X, SPAs, or sites with Shadow DOM.

aden-hive/hive · 40 tokens

hive.note-taking

Maintain a free-form scratchpad of decisions, extracted values, and open questions so context pruning doesn't lose anything you still need.

aden-hive/hive · 30 tokens

security-compliance

Guides security professionals in implementing defense-in-depth security architectures, achieving compliance with industry frameworks (SOC2, ISO27001, GDPR, HIPAA), conducting threat modeling and risk assessments, managing security operations and incident response, and embedding security throughout the SDLC.

sangrokjung/claude-forge · 56 tokens