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.
/plugin marketplace add bonfire-systems/goalkeeper/plugin install goalkeeperWrote 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.
[](https://agentmods.dev/skills/bonfire-systems/goalkeeper/goal-chain)<a href="https://agentmods.dev/skills/bonfire-systems/goalkeeper/goal-chain"><img src="https://agentmods.dev/badge/skills/bonfire-systems/goalkeeper/goal-chain/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.
<a href="https://agentmods.dev/skills/bonfire-systems/goalkeeper/goal-chain"><img src="https://agentmods.dev/badge/skills/bonfire-systems/goalkeeper/goal-chain.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00051 | $0.02287 |
| Opus 5 | $0.00026 | $0.01144 |
| Sonnet 5 | $0.00010 | $0.00457 |
| Haiku 4.5 | $0.00005 | $0.00229 |
Grade A, and why
goal-chain scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are operating the goal-chain skill. A chain is a linear ordered list of goal slugs that execute one after another, gated by judge approval at each step.
The gk CLI (python3 "${CLAUDE_PLUGIN_ROOT}/scripts/gk.py", abbreviated gk) owns all chain mechanics: parsing and validating the chain file, cursor movement, link approvals, and next-goal activation. You orchestrate: spawn executor → spawn judge → let gk verdict apply the outcome → act on what it prints.
Modes
- Start mode —
argsis a non-empty path to a chain file. Begin a new chain. - Status mode —
args == "status"or a chain exists and the user asks plainly. Show progress.
(There is no separate "advance mode" anymore — gk verdict <slug> approve advances the cursor atomically as part of applying the verdict.)
Start mode
Triggered by /goal-chain "<path/to/chain.md>".
1. Start the chain
gk chain-start <path/to/chain.md>
gk parses the file (frontmatter name: plus a numbered or bulleted slug list, # comments stripped), verifies every slug has a contract.md (a missing contract aborts start — prep all contracts up front so the chain definition is reviewable), refuses to start over an active goal or chain, writes chain.json, and activates the first slug. It prints NEXT: <slug> on success; on refusal, relay its message to the user (usually: run /goal-prep for missing slugs, or /goal-clear first).
2. Spawn the executor subagent
Chains run per-goal implementation in a fresh-context subagent — main context only orchestrates. This keeps main-context cost flat (~10K tokens per goal) so a many-goal chain completes in one session.
Use the Agent tool with subagent_type: general-purpose. Assemble a self-contained prompt:
- The full
contract.md— verbatim. - The compacted log — output of
gk log <slug> --compact(activation entry, every judge block, recent checkpoints — includes any fix-list if this is a re-spawn after rejection). - Chain context — chain name, current step N of total, the prior link's approval timestamp.
- Repo state —
git rev-parse HEAD,git status --porcelain(first 20 lines). - The directive — the template below, with
<GK>replaced by the resolved absolute gk command (e.g.python3 /path/to/goalkeeper/scripts/gk.py) — the subagent does not inherit${CLAUDE_PLUGIN_ROOT}:
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.
- 9d ago First seen · 149 lines · 51 tokens per session scan A 138709a8c206
goal-chain is a skill published in the GitHub repository bonfire-systems/goalkeeper (12 stars, last pushed 9d ago), licensed MIT. It adds 51 tokens to every session and 2,287 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 2026-08-30.
Other skills, from other repositories
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…
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…
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.
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…
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.
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.