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 skills/justinjdev/fellowship/retronpx skills add justinjdev/fellowship --skill retrogit 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 | $0.00032 | $0.01490 |
| Opus 5 | $0.00016 | $0.00745 |
| Sonnet 5 | $0.00006 | $0.00298 |
| Haiku 4.5 | $0.00003 | $0.00149 |
Grade A, and why
retro 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 2d 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 — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Retro — Post-Fellowship Retrospective
Overview
Analyzes a completed fellowship's history to surface patterns and interactively offer configuration improvements. Reads gate events, palantir alerts, and git metrics across all quest worktrees, then presents findings and walks through actionable recommendations one by one.
When to Use
- Manual: invoke
/retroafter a fellowship completes or is disbanded - Suggested: Gandalf suggests running
/retroduring the disband flow (not enforced)
Process
Step 1: Locate Fellowship Data
- Find the git root directory
- Read
~/.claude/fellowship.jsonto check for a customdataDirsetting. If absent, use the default data directory (.fellowship/). - Read
fellowship-state.jsonfrom the resolved data directory to enumerate all quest worktrees and their metadata - If no fellowship state file exists, report "No fellowship state found — nothing to analyze" and stop
Step 2: Collect Data
For each quest worktree listed in fellowship-state.json:
-
Gate events: Read
quest-herald.jsonlfrom the worktree's data directory via the Read tool. Each line is a JSON object withtimestamp,quest,type,phase, anddetailfields. Collect all entries of typegate_approved,gate_rejected,gate_submitted, andphase_transition. -
Quest state: Read
quest-state.jsonfrom the worktree's data directory. Record the finalphase,quest_name, and whether the quest completed. -
Quest tome: Read
quest-tome.jsonfrom the worktree's data directory if it exists. Record gate history (approved/rejected counts per phase), phases completed with durations, and files touched. -
Git metrics: Run these Bash commands for each worktree:
git -C {worktree} log --oneline | wc -l— commit countgit -C {worktree} diff --stat "$(git -C {worktree} rev-list --max-parents=0 HEAD | tail -n1)"..HEAD 2>/dev/null || echo "0 files changed"— change summary
-
Palantir alerts: Read
palantir-alerts.jsonlfrom the resolved data directory at the git root if it exists. Each line is a JSON object withtimestamp,type(stuck/drift/conflict/health/bulletin), anddetail. Standard alerts includequests; bulletin alerts includesource_quest,target_quest,topic, anddiscoveryinstead.
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.
- 2d ago First seen · 145 lines · 32 tokens per session scan A ea5104a53c97
retro is a skill published in the GitHub repository justinjdev/fellowship (5 stars, last pushed 19d ago), licensed Apache-2.0. It adds 32 tokens to every session and 1,490 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 skills, from other repositories
orbit
Running autonomous loops for nexus-autoloop. Generates script sets from goals, designs operation contracts, audits live loops, and recovers state — runners that complete reliably.
loom
Designing a repository's operating layer — which project-local skills, recipes, and orchestration workflows it needs, as one system. Not for a single skill body (Sigil) or runtime routing (Nexus).
titan
Delivering working code fastest via build-first product delivery through minimum agent chains; S/M scopes skip planning and build immediately. Use when compressing time-to-first-PR.
darwin
Orchestrating ecosystem self-evolution: lifecycle-phase detection, agent relevance, cross-agent knowledge synthesis, evolution proposals. Use when auditing skill-ecosystem health or fitness.
architect
Designing new skill agents via gap analysis, overlap detection, SKILL.md + reference generation, and Nexus integration. Not for task orchestration (Nexus) or format-only audits (Gauge).
cast
Casting personas: rapid generation from diverse inputs, registry-based persistence and lifecycle, data-driven evolution, inter-agent sync. Not for UI walkthroughs (Echo) or user research (Field).