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.
npx agentmods add instructions/tikoci/rosetta/pr-review-botsgit clone --depth 1 https://github.com/tikoci/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/instructions/tikoci/rosetta/pr-review-bots)<a href="https://agentmods.dev/instructions/tikoci/rosetta/pr-review-bots"><img src="https://agentmods.dev/badge/instructions/tikoci/rosetta/pr-review-bots.svg" alt="Measured on agentmods" 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 | $0.01266 | $0.01266 |
| Opus 5 | $0.00633 | $0.00633 |
| Sonnet 5 | $0.00253 | $0.00253 |
| Haiku 4.5 | $0.00127 | $0.00127 |
Grade A, and why
rosetta pr-review-bots.instructions.md 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 4d 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PR review bots (Copilot + CodeRabbit)
This is the rationale doc. For the runnable step-by-step procedure (list unresolved
threads, resolve them, re-check after a push), use the pr-review-gate skill
(.github/skills/pr-review-gate/SKILL.md) instead of re-deriving the gh commands here.
When a rosetta PR is marked Ready for Review (not while it is a draft), two
bots review it: copilot-pull-request-reviewer and coderabbitai. They surface
their findings through different GitHub mechanisms, so an agent that checks only
one signal will mis-read the state of the PR.
- CodeRabbit is a status check, not a findings gate. Its check turns green when
its review run finishes — green means "CodeRabbit is done looking," not "your
findings are addressed." Do not read a green CodeRabbit check as permission to merge.
It re-reviews on demand via an
@coderabbitai reviewPR comment. - Copilot is a requested reviewer. Its review lands as state
COMMENTED, neverCHANGES_REQUESTED. Sogh pr view N --json reviewDecisionwill not show it as blocking or pending the way a human "changes requested" review would — the findings are real but invisible to a decision-status check. - Bot reviews don't move
reviewDecision, but unresolved threads DO block the merge.mainis branch-protected: required status checks (test, both CodeQLAnalyze) plus required conversation resolution, withenforce_admins: false(an admin can still override the button, or merge viagh). Because both bots submitCOMMENTED(neverCHANGES_REQUESTED),gh pr view N --json reviewDecisionstays clean — the block surfaces asmergeStateStatus: BLOCKED, driven by the unresolved review threads, not by a review decision. SoreviewDecisionis not the signal to watch; an open bot thread is. Resolving every thread (below) is what clears the gate.
Wrapping a PR
Findings live in inline review comments, which gh pr view does not show. Read
them explicitly, then close the loop:
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.
- 4d ago First seen · 80 lines · 1,266 tokens per session scan A 3589e4a751db
rosetta pr-review-bots.instructions.md is an instructions file published in the GitHub repository tikoci/rosetta (43 stars, last pushed 18d ago), licensed MIT. It adds 1,266 tokens to every session, about $0.0063 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.
Other instructions, from other repositories
bun-mcp copilot-instructions.md
Copilot instructions for TomasHubelbauer/bun-mcp, covering github copilot instructions for the bun-mcp repository and formatting.
rosetta AGENTS.md
AGENTS.md instructions for griddynamics/rosetta: Main goal: cover E2E AI PDLC engineering workflows at foundation level for AI-First SDLC in enterprise. Top-level or orchestrator agents MUST READ docs/ARCHITECTURE.md contains technical details and guidance, and docs/CONTEXT.md - business context. Subagents - when…
mcp-server-azure-devops AGENTS.md
Instructions for Tiberriver256/mcp-server-azure-devops: /home/tiberriver256/repos/mcp-server-azure-devops/docs/important-knowledge/azure-devops-rest-api-research.md Researching Azure DevOps REST APIs, selecting api-version, or handling Azure DevOps Server (on-prem) endpoints.
plugin-files-mode
Rosetta Plugin Mode Bootstrap.
calc-mcp CLAUDE.md
Claude Code instructions for coo-quack/calc-mcp, covering project rules, tech stack, commands, project structure and tool architecture.
mcp-security-scanner CLAUDE.md
Instructions for badchars/mcp-security-scanner, covering mcp-security-scanner — mcp security scanner, architecture, key rules, tool categories (43 tools) and commands.