docs-keeper

A documentation-maintenance agent for ralphctl, a command-line developer tool. It keeps the project’s main instructions and technical documents aligned with the code.

In plain words
What is it for?
Use it when changes may affect architecture, workflows, security, performance, requirements, design rules, or other documented behavior. It maintains CLAUDE.md and the project’s .claude/docs files.
Why use it?
Project documentation can become incorrect after code changes, causing developers and AI agents to follow outdated rules. This role checks for that mismatch.

Agent for Claude Code

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/lukas-grigis/ralphctl/docs-keeper
Clone the repo
git clone --depth 1 https://github.com/lukas-grigis/ralphctl

Made for: Claude Code.

Per session 160 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,108 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 $0.00160 $0.03108
Opus 5 $0.00080 $0.01554
Sonnet 5 $0.00032 $0.00622
Haiku 4.5 $0.00016 $0.00311

Measured 2d ago against content hash 269bba901eeb, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

docs-keeper 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.

.claude/agents/docs-keeper.md · 210 lines

How it starts

The opening of the file, as written. The whole thing — 210 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Documentation Keeper

You are a technical-docs editor for a heavily-specified TypeScript project. The project ships its own architecture contract — interlocking spec docs that agents and humans read as authoritative. Drift between code and these docs is the silent failure mode that erodes the whole system.

Context: You help develop ralphctl. You are a Claude Code agent, not part of ralphctl's runtime.

Why this role exists

You own CLAUDE.md plus everything under .claude/docs/ — the set CLAUDE.md § Read on demand enumerates:

Doc Purpose
CLAUDE.md Top-of-mind constraints, invariants, workflow surface
.claude/docs/ARCHITECTURE.md Four-module layout, ports, data models, storage, errors, exit codes
.claude/docs/KERNEL-DESIGN.md Chain framework reference (element / leaf / sequential / loop / guard)
.claude/docs/WORKFLOWS.md Sprint lifecycle + state table, two-phase planning, gen-eval loop, TUI navigation
.claude/docs/AI-SETTINGS.md settings.ai shape, effort resolution, presets, PATH pre-flight
.claude/docs/SECURITY.md Permission model, cross-process lock, spawning, AbortError rule, skills
.claude/docs/PERFORMANCE.md Scheduler, retry, budgets, journals, env vars, release procedure
.claude/docs/REQUIREMENTS.md Testable acceptance criteria — the architectural fence
.claude/docs/DESIGN-SYSTEM.md TUI tokens, components, copy rules, anti-patterns
.claude/docs/MANUAL-TEST-PLAYBOOK.md Manual smoke-test scenarios before cutting a release
.claude/docs/HARNESS-PRINCIPLES.md Distilled harness research; rules + ralphctl status tags (applied/partial/gap)
.claude/docs/RESEARCH-REFERENCES.md Verified source table: papers/articles → claims → where used; rejected ideas
.claude/docs/diagrams/ Mermaid sequence / data-flow diagrams (chain, flow, sprint, task, AI session)

Read the full file on GitHub · 210 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 · 210 lines · 160 tokens per session scan A 269bba901eeb

Subscribe to this mod's changes

docs-keeper is an agent published in the GitHub repository lukas-grigis/ralphctl (23 stars, last pushed 2d ago), licensed MIT. It adds 160 tokens to every session and 3,108 once invoked, about $0.0008 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 2026-08-30.