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/settingsgit 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 | $0.00030 | $0.01564 |
| Opus 5 | $0.00015 | $0.00782 |
| Sonnet 5 | $0.00006 | $0.00313 |
| Haiku 4.5 | $0.00003 | $0.00156 |
Grade A, and why
settings 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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Config — Fellowship Settings Manager
Steps
Step 1: Read Config Layers
Read both config files (neither is required to exist):
- Project config:
.fellowship/config.jsonin the git repository root (find withgit rev-parse --show-toplevel) - User config:
~/.claude/fellowship.json
Note which keys are present in each file. The effective value for each key follows this precedence: defaults → project → user (user always wins).
Step 2: Show Settings
Present the merged config as a table with a Source column showing [default], [project], or [user] for each key:
Fellowship Config
Setting Value Source
─────────────────────────────────────────────────────────
branch.pattern null [default]
branch.author null [default]
branch.ticketPattern [A-Z]+-\d+ [default]
worktree.enabled true [default]
worktree.directory null [default]
gates.autoApprove [] [default]
pr.draft false [default]
pr.template null [default]
palantir.enabled true [default]
palantir.minQuests 2 [default]
issues.autoClose true [default]
models.quest null (inherit) [default]
models.scout null (sonnet) [default]
models.palantir null (haiku) [default]
models.balrog null (inherit) [default]
models.explore null (haiku) [default]
models.validator null (sonnet) [default]
User config: ~/.claude/fellowship.json
Project config: .fellowship/config.json (none found)
Show both file paths at the bottom, noting "(none found)" if a file doesn't exist.
Step 3: Ask What to Change
Ask the user what they'd like to change. Use AskUserQuestion with these options:
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 · 106 lines · 30 tokens per session scan A b78a948fea15
settings is a command published in the GitHub repository justinjdev/fellowship (5 stars, last pushed 18d ago), licensed Apache-2.0. It adds 30 tokens to every session and 1,564 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.