008-documentation

An agent task for documenting how project context and memory are organized. It covers workspace, project, plan, and agent levels, along with the guides and files that explain them.

In plain words
What is it for?
Use it to document the context hierarchy, memory practices, workspace setup, root documents, and related README guidance.
Why use it?
It makes inherited instructions, shared discoveries, decisions, and workspace setup easier to understand and maintain.

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/paulbreuler/limps/008-documentation
Clone the repo
git clone --depth 1 https://github.com/paulbreuler/limps
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 437 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 $0.00000 $0.00437
Opus 5 $0.00000 $0.00218
Sonnet 5 $0.00000 $0.00087
Haiku 4.5 $0.00000 $0.00044

Measured 2d ago against content hash f289b3a7e4bf, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

008-documentation 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.

plans/0047-limps-context-hierarchy/agents/008-documentation.md · 72 lines

What it actually says

Agent 008: Documentation

Objective

Document the context hierarchy and memory system comprehensively.

Tasks

  1. Context hierarchy guide (docs/context-hierarchy.md)

    • Workspace → Project → Plan → Agent hierarchy
    • How inheritance works (CSS-like cascade)
    • Override mechanisms
    • Root document types (vision, brand, architecture, NFRs)
  2. Memory system guide (docs/memory-system.md)

    • Agent memory: findings, decisions, blockers
    • Plan memory: shared discoveries, lessons
    • When to use each type
    • Memory CLI reference
  3. Workspace setup guide (docs/workspace-setup.md)

    • limps workspace init walkthrough
    • Recommended directory structure
    • Template workspace.md
    • Best practices for root documents
  4. README updates

    • Add context hierarchy section
    • Link to detailed guides
    • Quick examples

Key Topics to Cover

Context Hierarchy

  • Why inheritance matters (prevents drift)
  • Layer priorities explained
  • How to override workspace defaults
  • Staleness warnings and what to do

Memory System

  • White-box memory philosophy
  • Agent memory best practices
  • Promoting to plan memory
  • Session logging workflow

Root Documents

  • vision.md: North star, mission
  • brand.md: Terminology, tone
  • architecture.md: Technical principles
  • nfrs.md: Security, performance

Acceptance Criteria

  • All CLI commands documented with examples
  • Inheritance rules clearly explained
  • Memory workflow guides included
  • Root document templates provided
  • Follows existing docs style
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 · 72 lines · 0 tokens per session scan A f289b3a7e4bf

Subscribe to this mod's changes

008-documentation is an agent published in the GitHub repository paulbreuler/limps (10 stars, last pushed 6mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 437 tokens. 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