init-workspace-flow-state

A recorded setup report for a Rosetta workspace, showing its files, documentation, agents, skills, and progress through setup phases. Rosetta is a project framework for organizing coding-agent work.

In plain words
What is it for?
Checking workspace state, reviewing the file inventory, seeing which setup phases are complete, and identifying missing documentation such as a requirements index.
Why use it?
It gives the agent a snapshot of what workspace preparation has finished and which files are missing. This reduces uncertainty before later tasks use the workspace.

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/griddynamics/rosetta/init-workspace-flow-state
Clone the repo
git clone --depth 1 https://github.com/griddynamics/rosetta
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 1,562 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 $0.01562
Opus 5 $0.00000 $0.00781
Sonnet 5 $0.00000 $0.00312
Haiku 4.5 $0.00000 $0.00156

Measured 2d ago against content hash 7e9b0a89dfc9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

init-workspace-flow-state 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.

agents/init-workspace-flow-state.md · 143 lines

How it starts

The opening of the file, as written. The whole thing — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Init Workspace Flow State

State

  • mode: upgrade
  • plugin_active: false
  • composite: false
  • file_count: 512
  • status: COMPLETE
  • completed: 2026-03-27

File Inventory

File Status
docs/CONTEXT.md exists
docs/ARCHITECTURE.md exists
docs/TODO.md exists
docs/ASSUMPTIONS.md created
docs/TECHSTACK.md created
docs/DEPENDENCIES.md created
docs/CODEMAP.md created
docs/REQUIREMENTS/INDEX.md missing
docs/PATTERNS/INDEX.md created
agents/IMPLEMENTATION.md exists
agents/MEMORY.md exists
gain.json created

Phase Progress

Phase Status Notes
1 context complete upgrade mode, single repo, partial files
2 shells complete 17 skills + 7 agents + 12 commands + bootstrap rule — 2026-03-27
3 discovery complete TECHSTACK, CODEMAP, DEPENDENCIES created; file_count=512
4 rules skipped default disabled
5 patterns complete 13 patterns extracted into docs/PATTERNS/; INDEX.md and CHANGES.md created — 2026-03-27
6 documentation complete ASSUMPTIONS.md created, gain.json created, IMPLEMENTATION.md updated, MEMORY.md verified
7 questions complete HITL gaps documented in Gaps Identified section
8 verification complete All checkpoints passed — 2026-03-27

Phase 2 Shell Files

Skills Created (17 new proxy shells)

  • .claude/skills/load-context/SKILL.md
  • .claude/skills/coding/SKILL.md
  • .claude/skills/coding-agents-farm/SKILL.md
  • .claude/skills/coding-agents-prompt-adaptation/SKILL.md
  • .claude/skills/coding-agents-prompt-authoring/SKILL.md
  • .claude/skills/debugging/SKILL.md
  • .claude/skills/large-workspace-handling/SKILL.md
  • .claude/skills/natural-writing/SKILL.md
  • .claude/skills/planning/SKILL.md
  • .claude/skills/questioning/SKILL.md
  • .claude/skills/reasoning/SKILL.md
  • .claude/skills/requirements-authoring/SKILL.md
  • .claude/skills/requirements-use/SKILL.md
  • .claude/skills/research/SKILL.md
  • .claude/skills/reverse-engineering/SKILL.md
  • .claude/skills/tech-specs/SKILL.md
  • .claude/skills/testing/SKILL.md

Read the full file on GitHub · 143 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 · 143 lines · 0 tokens per session scan A 7e9b0a89dfc9

Subscribe to this mod's changes

init-workspace-flow-state is an agent published in the GitHub repository griddynamics/rosetta (341 stars, last pushed 4d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 1,562 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 2026-08-30.

Related

Other agents, from other repositories

builder

Turn shot-plan.json into one renderable HyperFrames composition (compositions/index.html). Everything stays in the HF ecosystem — HTML is the source of truth; a single paused GSAP timeline carries all motion; the engine seeks it. Category-specific build rules live in categories/ /module.md; this file is the shared…

calesthio/OpenMontage · 0 tokens

test

Give your AI agent n8n superpowers. 537 nodes with full schemas, 7,700+ templates, Git-like sync, and TypeScript workflows.

EtienneLescot/n8n-as-code · not measured

clawteam-dev-manager

Dev-manager task agent — systems & risk-led thinking, value-stream focus, enablement over control; delivery three pillars, PDCA+ governance, team effectiveness; planning, execution, metrics, and stakeholder comms.

deepelementlab/jupyter-studio · 49 tokens

clawteam-rnd-frontend

Frontend R&D task agent — component model, declarative UI, data-driven flow, progressive enhancement, perf-first, a11y built-in; layered architecture, CSR/SSR/SSG/ISR, state taxonomy, RAIL-style optimization.

deepelementlab/jupyter-studio · 57 tokens

clawteam-system-architect

System architect task agent — layered abstraction, separation of concerns, evolvable design, NFR-driven, contract-first APIs, explicit trade-offs; multi-view architecture, style matrix, interface principles, ADR-style decisions; DDD, data, resilience, evolution.

deepelementlab/jupyter-studio · 59 tokens

designteam-interaction-designer

IXD task agent — path enumeration, cognitive de-entropy, feedback loops, physical metaphors, forgiveness; Fitts, Hick, Gestalt, mental-model fit, Tesler, peak-end, Occam, isolation; flows, states, rules, motion, spec for dev.

deepelementlab/jupyter-studio · 64 tokens