init-workspace-verification

A final workspace setup audit that checks whether the required project notes and initialization steps are complete.

In plain words
What is it for?
Use it to verify technology notes, code maps, dependencies, architecture, assumptions, and agent memory, and to document any justified exceptions.
Why use it?
It helps catch missing, empty, misplaced, or inconsistent setup information before work begins.

Skill for Claude CodeCodex

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/griddynamics/rosetta/init-workspace-verification
Any agent
npx skills add griddynamics/rosetta --skill init-workspace-verification
Clone the repo
git clone --depth 1 https://github.com/griddynamics/rosetta

Made for: Claude Code, Codex.

Per session 10 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 744 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 $0.00010 $0.00744
Opus 5 $0.00005 $0.00372
Sonnet 5 $0.00002 $0.00149
Haiku 4.5 $0.00001 $0.00074

Measured 3d ago against content hash aab895343737, 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-verification 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 3d 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.

instructions/r2/core/skills/init-workspace-verification/SKILL.md · 92 lines

What it actually says

<init_workspace_verification>

Senior workspace initialization auditor

<when_to_use_skill> Final phase of workspace initialization. Consolidates all init-phase outputs into a single completeness audit, runs catch-up for gaps, and revalidates assumptions. </when_to_use_skill>

<core_concepts>

  • All Rosetta prep steps MUST be FULLY completed, load-context skill loaded and fully executed

</core_concepts>

Run every checkpoint. Each must pass or have documented justification.

FILE EXISTENCE (non-empty, correct scope):

  1. TECHSTACK.md — detected technologies, frameworks, build tools
  2. CODEMAP.md — markdown headers, 3-4 levels, recursive children counts
  3. DEPENDENCIES.md — direct dependencies only (project, package, version)
  4. CONTEXT.md — business context only, no technical details
  5. ARCHITECTURE.md — technical architecture, references CODEMAP.md, no business context
  6. IMPLEMENTATION.md — current state, DRY references
  7. ASSUMPTIONS.md — unknowns with forward references
  8. AGENT MEMORY.md — self-defined purpose and initial entries
  9. Each document includes self-definition (purpose, content type, style)

INIT INTEGRITY:

  1. Init mode: exactly one of install, upgrade, plugin
  2. Composite workspace: top-level docs as registries if composite
  3. File inventory built before creation/update decisions
  4. Shell files: frontmatter + single ACQUIRE, zero inline logic
  5. load-context shell and bootstrap rule installed
  6. Shells match schema — no structural deviations, no absolute paths
  7. docs/PATTERNS/ with INDEX.md; each pattern in 2+ locations; INDEX.md is consistent

CROSS-FILE CONSISTENCY:

  1. TECHSTACK frameworks appear in ARCHITECTURE
  2. CONTEXT, ARCHITECTURE, IMPLEMENTATION complement — no duplication
  3. coding.md ACQUIRED FROM KB and used as file creation reference
  4. greppable headers used in all files

CONDITIONAL (if rules requested, N/A otherwise):

  1. KB SEARCHED for IDE/Agent rules — agent's built-in knowledge is obsolete, verify KB was queried
  2. Existing rules checked before creating new
  3. Root agents file uses bootstrap.md template
  4. Tech-specific agent files created
  5. Local instructions with MoSCoW emphasis
  6. Weekly check mechanism with release version
  7. Subagents/commands initialized via KB instructions if supported

QUESTIONS:

  1. HIGH priority gaps addressed via targeted questions

CATCH-UP: For failed checkpoints — identify owning skill, execute, re-verify.

ASSUMPTIONS REVALIDATION:

  • Resolved entries: mark with evidence
  • Duplicates: keep most detailed
  • Forward references: verify target files exist
  • New assumptions: track any discovered during verification

DEPRECATED ARTIFACTS (notify user, do NOT auto-delete):

  • agents/init-rosetta-shells-flow-state.md — r1 state file
  • Local init-rosetta-shells-flow.md — replaced by init-workspace-shells skill

</init_workspace_verification>

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. 3d ago First seen · 92 lines · 10 tokens per session scan A aab895343737

Subscribe to this mod's changes

init-workspace-verification is a skill published in the GitHub repository griddynamics/rosetta (341 stars, last pushed 5d ago), licensed Apache-2.0. It adds 10 tokens to every session and 744 once invoked, about $0.0001 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.