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 agentmods add commands/justinjdev/fellowship/scribegit clone --depth 1 https://github.com/justinjdev/fellowshipWhat 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 | $0.00038 | $0.00724 |
| Opus 5 | $0.00019 | $0.00362 |
| Sonnet 5 | $0.00008 | $0.00145 |
| Haiku 4.5 | $0.00004 | $0.00072 |
Grade A, and why
scribe 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 yesterday.
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 — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Forge Template — Create Quest Templates
Overview
Creates quest templates that encode project-specific knowledge — conventions Claude wouldn't know, domain rules that aren't in code, team workflows that matter. Templates are worthless if they contain generic advice ("write tests," "follow patterns"). They're valuable when they capture things like "payments changes require idempotency tests" or "all API routes need OpenAPI spec updates."
When to Use
- Setting up fellowship for a new project
- After noticing quests repeatedly miss a project convention
- When a category of work has domain-specific requirements
Process
1. Gather Context
Ask the user:
- What kind of quest is this template for? (e.g., "API endpoint," "database migration," "UI component," not generic categories like "bugfix")
- What do quests of this type consistently get wrong or miss? This is the core value — things Claude wouldn't infer from code alone.
- Are there project-specific gates or checks? (e.g., "security review required for auth changes," "design approval before UI work")
Then investigate the codebase:
- Read CLAUDE.md, CONTRIBUTING.md, and any project conventions docs
- Look at recent PRs or commits of the same type for patterns
- Identify project-specific tooling, scripts, or workflows (e.g., custom test runners, migration generators, code generators)
2. Draft the Template
Write a template with YAML frontmatter and phase-specific sections. Every line of guidance must be specific to this project — if the advice would apply to any codebase, delete it.
Format:
---
name: {name}
description: {one-line description}
keywords: [{comma-separated trigger words}]
---
## Research Guidance
{project-specific research steps}
## Plan Guidance
{project-specific planning constraints}
## Implement Guidance
{project-specific implementation rules}
## Review Guidance
{project-specific review checklist}
Rules for good templates:
- Every bullet must reference something concrete: a file path, a tool, a convention, a domain rule
- If you can't point to a specific project artifact or convention, the bullet doesn't belong
- Keywords should match how the user naturally describes this kind of work
- Fewer, sharper bullets beat comprehensive generic lists
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.
- yesterday First seen · 85 lines · 38 tokens per session scan A 3fbaeaf1badd
scribe is a command published in the GitHub repository justinjdev/fellowship (5 stars, last pushed 18d ago), licensed Apache-2.0. It adds 38 tokens to every session and 724 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 2026-08-31.
Other commands, from other repositories
auto-mode
Idea-to-running-code lifecycle orchestration. 10-phase pipeline with 5 hard decision gates, wave-based parallelism, and STATE.json resumability. Composes /deep-research, /auto-swarm-nth, /production-upgrade, /security-audit, and /ship into a single end-to-end flow.
max-research
Nuclear-scale autonomous research — deploys 500-1000 agents in ONE massive simultaneous wave for exhaustive topic saturation. Deep-research methodology × auto-swarm scale = maximum parallel intelligence. WARNING: Extreme resource consumption.
omni-plan
ProductionOS flagship — 13-step orchestrative pipeline with tri-tiered evaluation, recursive convergence, CEO/Eng/Design review chain, CLEAR framework evaluation, multi-model judge tribunal, and autonomous PIVOT/REFINE/PROCEED decisions. Targets 100% production-ready output.
auto-swarm-nth
Nth-iteration agent swarm — spawns parallel agent waves, evaluates strictly per wave, re-swarms gaps until 100% coverage and 10/10 quality. Can invoke any ProductionOS skill or command within waves.
frontend-upgrade
Full-stack frontend upgrade pipeline — fuses /production-upgrade iterative audit with /plan-ceo-review vision and /plan-eng-review rigor. Deploys parallel auto-swarm agents for iterative audit and execution. Enriched with /deep-research for competitive parity.
omni-plan-nth
Nth-iteration omni-plan — recursive orchestration that chains ALL ProductionOS skills and agents, evaluates strictly per iteration, and loops until 10/10 is achieved. Each iteration can invoke any command or skill in the system.