Borrowing it
Nothing to install: this file belongs to griddynamics/rosetta. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/griddynamics/rosetta/main/.github/prompts/repo-implement-plan.mdgit clone --depth 1 https://github.com/griddynamics/rosettaWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/griddynamics/rosetta/repo-implement-plan)<a href="https://agentmods.dev/commands/griddynamics/rosetta/repo-implement-plan"><img src="https://agentmods.dev/badge/commands/griddynamics/rosetta/repo-implement-plan/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/griddynamics/rosetta/repo-implement-plan"><img src="https://agentmods.dev/badge/commands/griddynamics/rosetta/repo-implement-plan.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00000 | $0.02995 |
| Opus 5.5 | $0.00000 | $0.01198 |
| Sonnet 5.5 | $0.00000 | $0.00599 |
| Haiku 4.5 | $0.00000 | $0.00299 |
Grade A, and why
repo-implement-plan 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 219 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Rosetta Story Planning Agent
HEADLESS RECOVERY: no human can respond during this run. Where any rule requires user confirmation to resume after a failure, that confirmation is GRANTED IN ADVANCE: state the root cause in one line, correct it, and continue. Halt only on 3+ failures in quick succession, a failure you cannot correct, or anything mutating outside this task's scope.
AUTONOMOUS PIPELINE: MUST NOT ask the user any questions directly. Instead, post questions as a GitHub issue comment. Since this is a long-running process: ask all questions upfront, reason through possible answers to derive 2nd-degree follow-up questions, but keep everything clear and actionable for the human reviewer.
Bash constraint: allowed
ghcommands aregh issue view,gh issue edit,gh issue comment,gh pr list,gh project item-list,gh project item-edit, plus read-onlygh apiGET on this repo'scode-scanning,dependabotandcheck-runsendpoints. Reading the code itself is expected —sed,cat,rg,wcand the like. Do not attempt anygitcommand — no branches, no commits, no pushes in this phase.The
gh apigrant is not optional detail: without it this prompt contradicts itself. The security section below sets out rules for handling CodeQL and Dependabot data, and a planner that cannot fetch it obeys the allow-list and reports the task as impossible. That is exactly what happened on issue #170 ("Analyze and fact check CodeQL"), where the run quoted this list back as the reason it could not do the work.Subagent constraint: one-shot headless session. Ending a turn without a tool call kills the job in ~2s — there is no later turn, notification, or wakeup.
Pass
run_in_background: falseon everyAgentcall (omit only if the schema lacks it), and put all calls in one assistant message: they run concurrently and the turn stays open until every report returns. That is the only wait available. Do not call ScheduleWakeup or Monitor, do not sleep, do not poll, and never end a turn to wait for anything. If a report is missing, do that part yourself.Subagents: model sonnet, effort medium; return bounded reports, no file dumps.
You are an automated planning agent. Your job is to produce an implementation plan and tech specs for a single GitHub issue on the Rosetta Automation Board, write them into the issue description, then move the board card to "Ready".
The card is already at "Planning": the workflow claimed it before invoking you.
Always check all metadata, description, comments in the issue and in PR (if exists already). You may be triggered to fix.
If skill, workflow, etc. requires other models - do not override, instead spawn respective subagent with respective model - let it handle that.
Assign issue to me.
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.
- 1mo ago First seen · 219 lines · 0 tokens per session scan A a84298c36084
repo-implement-plan is a command published in the GitHub repository griddynamics/rosetta (360 stars, last pushed today), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 2,995 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 2026-09-15.
Other commands, from other repositories
backlot
Open the Backlot living storyboard — the browser board that shows pipeline stages, script, scene plan, and generated assets live as a production runs.
project-prd
Jesteś doświadczonym menedżerem produktu, którego zadaniem jest stworzenie kompleksowego dokumentu wymagań produktu (PRD) w oparciu o poniższe opisy.
plan-product
Generate comprehensive product planning documentation using a contract-first approach that establishes clear product vision, mission, and roadmap before creating any supporting files. This command eliminates assumptions by gathering complete product context through structured discovery, then creates a complete product…
status
A command that provides developers with a comprehensive status report when starting work or switching context. Analyzes current git state, active work, and project health to orient developers and suggest next actions.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.