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.
npx skills add CloseTheLoops/moradin --skill forgegit clone --depth 1 https://github.com/CloseTheLoops/moradinWrote 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/closetheloops/moradin/forge)<a href="https://agentmods.dev/skills/closetheloops/moradin/forge"><img src="https://agentmods.dev/badge/skills/closetheloops/moradin/forge/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/closetheloops/moradin/forge"><img src="https://agentmods.dev/badge/skills/closetheloops/moradin/forge.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 | $0.00054 | $0.01437 |
| Opus 5.5 | $0.00022 | $0.00575 |
| Sonnet 5.5 | $0.00011 | $0.00287 |
| Haiku 4.5 | $0.00005 | $0.00144 |
Grade A, and why
moradin-forge 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 1mo 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 — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
moradin:forge
The front door of the pipeline. You never guess what to do next in a forge project — this command reads the state and routes.
When invoked
/moradin:forge or /moradin:forge <what the operator wants to do>
Step 1 — Find the target project
The forge runs against a target project directory — always a SIBLING of the Moradin folder, never inside it (nesting tangles git and pollutes context). If the conversation already names it, use it. Otherwise ask: "Which project folder are we working in? (Give me a path, or a name and I'll create a new folder next to Moradin.)" For a brand-new project, create the sibling directory and git init it — explain in one sentence that git is the save-point system everything else relies on.
Step 2 — Read the journal first
Read .forge/journal.md in the target project. It is 3 lines: current stage, last action, next action.
- No
.forge/directory → first run. Go to Step 3 (Calibrate). - Journal exists → tell the operator where they are in one sentence ("You're mid-research; last time we compared databases. Next: run /moradin:decide.") Then route via Step 4.
Load other .forge/ files only when the route needs them — never all at once.
Step 3 — Calibrate (first run only)
Before asking anything: if this workshop has memory/preferences/ content, read its _INDEX.md and pre-fill what's already known about how this operator works. Confirm pre-filled answers in one line ("I know you try the app rather than read diffs — still true?") instead of re-asking.
Then a short plain-language interview for the gaps, a few questions at a time — never a wall. "I don't know what that is" is a real answer and means "not yet."
- What are you building here, in a sentence or two?
- When AI writes code for you — do you read it, skim it, or just try the app?
- Do you use git? Branches? Pull requests?
- Are there tests? Do you run them?
- How do you find out something broke?
- Ever wished you could rewind the project to yesterday? What happened?
- How much process do you want — light guardrails, or fuller structure that catches more?
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.
- 1mo ago First seen · 99 lines · 54 tokens per session scan A ec699b2ecf80
moradin-forge is a skill published in the GitHub repository CloseTheLoops/moradin (2 stars, last pushed 2mo ago), licensed MIT. It adds 54 tokens to every session and 1,437 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-08-31.
Other skills, from other repositories
ara-research-manager
Records research provenance as a post-task epilogue, scanning conversation history at the end of a coding or research session to extract decisions, experiments, dead ends, claims, heuristics, and pivots, and writing them into the ara/ directory with user-vs-AI provenance tags. Use as a session epilogue — never during…
work-on-ticket
Fetches Jira ticket details, creates an appropriately named branch, and initiates the task planning workflow. Use when the user says "work on [TICKETID]" or similar phrases.
unit-lane
One-shot lane conductor for a delivery unit: triage, implement, evidence, and close in a single document. Triggers: "unit-lane", "run the lane", "work on this feature/fix", "build this unit".
workflow-status
Read-only workflow sensor: run the deterministic script, read the fixed machine envelope, interpret the recommendation. Never edits. Triggers: "workflow-status", "workflow status", "what can I build next".
project-flow-ops
Use when projects or tasks need explicit state, WIP control, ownership, definitions of done, blocker handling, and verified closure.
llm-wiki-team-rollout
Plan and implement LLM-Wiki adoption for a team or company. Use for onboarding knowledge, bus factor, repo docs, decision records, PR-based agent writes, CODEOWNERS, permissions, governance, RACI/DACI, SLOs, review queues, team rituals, staffing, dashboards, security boundaries and operating models.