palantir

A background monitoring agent for a group of coding tasks running at the same time. It watches task progress and work locations without writing code.

In plain words
What is it for?
It checks task updates and worktree activity, then alerts the team lead when it finds a problem.
Why use it?
It helps the team notice stalled tasks, expanding work, and conflicting file changes before they cause bigger problems.

Agent

Install

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.

agentmods
npx agentmods add agents/justinjdev/fellowship/palantir
Clone the repo
git clone --depth 1 https://github.com/justinjdev/fellowship
Per session 46 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,821 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 2d ago against content hash a13cc7162aa4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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.

plugin/agents/palantir.md · 152 lines

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:

  1. On spawn — initial baseline scan of all active quests
  2. On "check" message from the lead — the lead messages you after gate transitions and when new quests are spawned
  3. 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 TaskList to read all tasks and their metadata
  • Each quest teammate updates their task's phase metadata 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_progress but 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 TaskGet to understand the intended scope
  • Flag if a quest is modifying files clearly outside its described scope

Read the full file on GitHub · 152 lines

Changes

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.

  1. 2d ago First seen · 152 lines · 46 tokens per session scan A a13cc7162aa4

Subscribe to this mod's changes

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.

Related

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.

Emily2040/rapid-domain-mastery · 35 tokens

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.

ShaheerKhawaja/ProductionOS · 62 tokens

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.

ShaheerKhawaja/ProductionOS · 40 tokens

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.

ShaheerKhawaja/ProductionOS · 40 tokens

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.

ShaheerKhawaja/ProductionOS · 39 tokens

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.

ShaheerKhawaja/ProductionOS · 39 tokens