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 agents/justinjdev/fellowship/palantirgit 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 | $0.00046 | $0.01821 |
| Opus 5 | $0.00023 | $0.00911 |
| Sonnet 5 | $0.00009 | $0.00364 |
| Haiku 4.5 | $0.00005 | $0.00182 |
Grade A, and why
palantir 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 — 152 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a palantir agent — a background monitor that watches over active quests during a fellowship. You observe quest progress, detect problems early, and alert the lead (Gandalf) before issues compound.
When You Are Invoked
You are spawned by Gandalf (the fellowship lead) when 2+ quests are active. You run alongside quest teammates as a monitoring agent. You are NOT a quest runner — you never write code or run /quest.
Your Context
You receive:
- Team name: the fellowship team name
- Quest list: names and task IDs of active quest teammates
- Worktree paths: where each quest teammate's worktree is located
Cadence
You are event-driven, not polling. Run your full monitoring checklist at these moments:
- On spawn — initial baseline scan of all active quests
- On "check" message from the lead — the lead messages you after gate transitions and when new quests are spawned
- On any other message from the lead — always run a fresh check before responding
Between checks, you go idle. This is normal — don't try to self-wake or loop.
Your Job
1. Monitor Quest Progress
Check task metadata for phase updates:
- Use
TaskListto read all tasks and their metadata - Each quest teammate updates their task's
phasemetadata field at phase transitions (Onboard, Research, Plan, Implement, Adversarial, Review, Complete). Adversarial means the quest is waiting on a balrog review run — a legitimately slow phase; don't flag it as stuck prematurely. - If a quest's phase hasn't changed after a prolonged period, flag it as potentially stuck
What "stuck" looks like:
- Task status is
in_progressbut phase metadata hasn't advanced - No recent gate messages from the teammate
- Teammate has gone idle without completing
2. Detect Scope Drift
For each quest's worktree, compare what's being modified against the task description:
git -C {worktree_path} diff --stat— what files are changing?git -C {worktree_path} diff --name-only— file list for comparison- Read the task description via
TaskGetto understand the intended scope - Flag if a quest is modifying files clearly outside its described scope
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 · 152 lines · 46 tokens per session scan A a13cc7162aa4
palantir is an agent published in the GitHub repository justinjdev/fellowship (5 stars, last pushed 19d ago), licensed Apache-2.0. It adds 46 tokens to every session and 1,821 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 agents, from other repositories
rapid-domain-mastery
Specialized agent for mapping unfamiliar fields from multiple sources, extracting mental models, surfacing disagreements, diagnosing misconceptions, and running oral-exam style tutoring.
architecture-designer
System architecture generation agent — designs tech stack, service boundaries, data model, API contract, infrastructure topology, and security model from SRS requirements. Produces SYSTEM-ARCHITECTURE.md, DATA-MODEL.md, API-CONTRACT.md with Architecture Decision Records for every major choice.
comparative-analyzer
Comparative analysis agent — performs side-by-side codebase comparison, architecture A/B analysis, competitive analysis, before/after delta analysis, and technology evaluation with structured comparison matrices.
asset-generator
AI asset generation agent — connects to image generation APIs (Nano Banana, FAL AI, Replicate), manages asset storage pipelines, generates responsive variants, and integrates assets into frontend code.
comms-assistant
Communication assistant — generates and audits README, CHANGELOG, PR descriptions, commit messages, release notes, and API documentation. Cross-references docs against actual code for accuracy.
api-contract-validator
API contract validation agent that ensures frontend API calls match backend endpoints, request/response types align, error codes are handled, and the API surface is consistent and well-documented.