james

A fresh-eyes review for plans, specifications, and other project documents, checking whether another agent could use them without hidden context.

In plain words
What is it for?
Use it after writing or significantly changing a concept, product requirements document, plan, design, strategy, or architecture proposal.
Why use it?
It finds missing explanations and assumptions that could make a document difficult to restart or follow later.

Skill for Claude CodeCodex

Part of the limitless plugin — 10 skills shipped together

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 skills/pyros-projects/limitless/james
Any agent
npx skills add pyros-projects/limitless --skill james
Clone the repo
git clone --depth 1 https://github.com/pyros-projects/limitless

Made for: Claude Code, Codex.

Or install limitless, the plugin that ships this one along with the rest of its 10 skills.

Per session 108 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,852 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 $0.00108 $0.01852
Opus 5 $0.00054 $0.00926
Sonnet 5 $0.00022 $0.00370
Haiku 4.5 $0.00011 $0.00185

Measured 2d ago against content hash 0e2bac6e6193, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

james 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.

plugins/limitless/skills/james/SKILL.md · 183 lines

How it starts

The opening of the file, as written. The whole thing — 183 lines — stays where its author put it; the contents beside it link to each section on GitHub.

James — Fresh Eyes For Documents

What James Does

James is the persistent constrained reviewer for planning documents. James checks whether a future agent, seeing only the document and the allowed project-owned context, can understand and act on it without hidden conversation, private memory, external files, or "you know what I mean" residue.

James is not a prose polish pass. James protects restartability.

Mandatory Triggers

Use this skill immediately after you write or materially edit:

  • a concept document
  • a PRD
  • a plan
  • a specification
  • a design document
  • a strategy document
  • an architecture or implementation proposal

Also use it whenever the user says "invoke James", "run James", "James this", "James-review", "ask James", or equivalent.

Do not use James for code review, article voice editing, ordinary research summaries, or the first drafting pass itself. Write the document first, then James reviews it.

Scope Envelope

Before spawning James, decide and state the allowed context envelope.

Rules:

  1. Project-owned only. James may see files inside the current project root. James may not use web search, QMD, global memories, private cross-project knowledge, this conversation, or files outside the project.
  2. Standalone docs default narrow. Concepts, PRDs, plans, specs, design docs, and strategy docs are reviewed as primary standalone artifacts: target document only, plus file path and project name. Add same-project context only when the document explicitly declares a dependency or the user explicitly names the context.
  3. Chronological notes may use older project context. Post-release ideas, retrospectives, release notes, migration notes, and follow-up notes may use same-project files older than the target. Prefer git history for age; if unavailable, use filesystem mtime and state the fallback.
  4. Narrower beats broader. If the user names a narrower scope, obey it. If the user asks for broader context, broader still means project-owned only.
  5. Missing context is a finding. If a claim can only be understood from chat history, memory, private paths, or external systems, James flags it. Do not broaden the scope to rescue the document.

Read the full file on GitHub · 183 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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 · 183 lines · 108 tokens per session scan A 0e2bac6e6193

Subscribe to this mod's changes

james is a skill published in the GitHub repository pyros-projects/limitless (9 stars, last pushed 20d ago), licensed MIT. It adds 108 tokens to every session and 1,852 once invoked, about $0.0005 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.